rockerritesh commited on
Commit
9662617
·
verified ·
1 Parent(s): 70a3c5c

Upload fine-tuned Whisper Tiny Maithili ASR model

Browse files
Files changed (50) hide show
  1. checkpoint-1000/config.json +59 -0
  2. checkpoint-1000/generation_config.json +268 -0
  3. checkpoint-1000/model.safetensors +3 -0
  4. checkpoint-1000/optimizer.pt +3 -0
  5. checkpoint-1000/preprocessor_config.json +14 -0
  6. checkpoint-1000/rng_state.pth +3 -0
  7. checkpoint-1000/scaler.pt +3 -0
  8. checkpoint-1000/scheduler.pt +3 -0
  9. checkpoint-1000/trainer_state.json +332 -0
  10. checkpoint-1000/training_args.bin +3 -0
  11. checkpoint-1500/config.json +59 -0
  12. checkpoint-1500/generation_config.json +268 -0
  13. checkpoint-1500/model.safetensors +3 -0
  14. checkpoint-1500/optimizer.pt +3 -0
  15. checkpoint-1500/preprocessor_config.json +14 -0
  16. checkpoint-1500/rng_state.pth +3 -0
  17. checkpoint-1500/scaler.pt +3 -0
  18. checkpoint-1500/scheduler.pt +3 -0
  19. checkpoint-1500/trainer_state.json +481 -0
  20. checkpoint-1500/training_args.bin +3 -0
  21. checkpoint-2000/config.json +59 -0
  22. checkpoint-2000/generation_config.json +268 -0
  23. checkpoint-2000/model.safetensors +3 -0
  24. checkpoint-2000/optimizer.pt +3 -0
  25. checkpoint-2000/preprocessor_config.json +14 -0
  26. checkpoint-2000/rng_state.pth +3 -0
  27. checkpoint-2000/scaler.pt +3 -0
  28. checkpoint-2000/scheduler.pt +3 -0
  29. checkpoint-2000/trainer_state.json +630 -0
  30. checkpoint-2000/training_args.bin +3 -0
  31. checkpoint-500/config.json +59 -0
  32. checkpoint-500/generation_config.json +268 -0
  33. checkpoint-500/model.safetensors +3 -0
  34. checkpoint-500/optimizer.pt +3 -0
  35. checkpoint-500/preprocessor_config.json +14 -0
  36. checkpoint-500/rng_state.pth +3 -0
  37. checkpoint-500/scaler.pt +3 -0
  38. checkpoint-500/scheduler.pt +3 -0
  39. checkpoint-500/trainer_state.json +183 -0
  40. checkpoint-500/training_args.bin +3 -0
  41. config.json +59 -0
  42. generation_config.json +268 -0
  43. model.safetensors +3 -0
  44. preprocessor_config.json +14 -0
  45. processor_config.json +17 -0
  46. runs/Mar14_14-23-02_68cebedf7b2a/events.out.tfevents.1773498182.68cebedf7b2a.5147.0 +3 -0
  47. runs/Mar14_14-23-02_68cebedf7b2a/events.out.tfevents.1773503728.68cebedf7b2a.5147.1 +3 -0
  48. tokenizer.json +0 -0
  49. tokenizer_config.json +127 -0
  50. training_args.bin +3 -0
checkpoint-1000/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 50257,
10
+ "classifier_proj_size": 256,
11
+ "d_model": 384,
12
+ "decoder_attention_heads": 6,
13
+ "decoder_ffn_dim": 1536,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 4,
16
+ "decoder_start_token_id": 50258,
17
+ "dropout": 0.0,
18
+ "dtype": "float32",
19
+ "encoder_attention_heads": 6,
20
+ "encoder_ffn_dim": 1536,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 4,
23
+ "eos_token_id": 50257,
24
+ "forced_decoder_ids": [
25
+ [
26
+ 1,
27
+ 50259
28
+ ],
29
+ [
30
+ 2,
31
+ 50359
32
+ ],
33
+ [
34
+ 3,
35
+ 50363
36
+ ]
37
+ ],
38
+ "init_std": 0.02,
39
+ "is_encoder_decoder": true,
40
+ "mask_feature_length": 10,
41
+ "mask_feature_min_masks": 0,
42
+ "mask_feature_prob": 0.0,
43
+ "mask_time_length": 10,
44
+ "mask_time_min_masks": 2,
45
+ "mask_time_prob": 0.05,
46
+ "max_source_positions": 1500,
47
+ "max_target_positions": 448,
48
+ "median_filter_width": 7,
49
+ "model_type": "whisper",
50
+ "num_hidden_layers": 4,
51
+ "num_mel_bins": 80,
52
+ "pad_token_id": 50257,
53
+ "scale_embedding": false,
54
+ "tie_word_embeddings": true,
55
+ "transformers_version": "5.3.0",
56
+ "use_cache": false,
57
+ "use_weighted_layer_sum": false,
58
+ "vocab_size": 51865
59
+ }
checkpoint-1000/generation_config.json ADDED
@@ -0,0 +1,268 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 2
6
+ ],
7
+ [
8
+ 3,
9
+ 0
10
+ ],
11
+ [
12
+ 3,
13
+ 2
14
+ ],
15
+ [
16
+ 3,
17
+ 3
18
+ ],
19
+ [
20
+ 3,
21
+ 4
22
+ ],
23
+ [
24
+ 3,
25
+ 5
26
+ ]
27
+ ],
28
+ "assistant_confidence_threshold": 0.4,
29
+ "assistant_lookbehind": 10,
30
+ "begin_suppress_tokens": [
31
+ 220,
32
+ 50257
33
+ ],
34
+ "bos_token_id": 50257,
35
+ "decoder_start_token_id": 50258,
36
+ "diversity_penalty": 0.0,
37
+ "do_sample": false,
38
+ "early_stopping": false,
39
+ "encoder_no_repeat_ngram_size": 0,
40
+ "encoder_repetition_penalty": 1.0,
41
+ "eos_token_id": 50257,
42
+ "epsilon_cutoff": 0.0,
43
+ "eta_cutoff": 0.0,
44
+ "forced_decoder_ids": null,
45
+ "is_multilingual": true,
46
+ "lang_to_id": {
47
+ "<|af|>": 50327,
48
+ "<|am|>": 50334,
49
+ "<|ar|>": 50272,
50
+ "<|as|>": 50350,
51
+ "<|az|>": 50304,
52
+ "<|ba|>": 50355,
53
+ "<|be|>": 50330,
54
+ "<|bg|>": 50292,
55
+ "<|bn|>": 50302,
56
+ "<|bo|>": 50347,
57
+ "<|br|>": 50309,
58
+ "<|bs|>": 50315,
59
+ "<|ca|>": 50270,
60
+ "<|cs|>": 50283,
61
+ "<|cy|>": 50297,
62
+ "<|da|>": 50285,
63
+ "<|de|>": 50261,
64
+ "<|el|>": 50281,
65
+ "<|en|>": 50259,
66
+ "<|es|>": 50262,
67
+ "<|et|>": 50307,
68
+ "<|eu|>": 50310,
69
+ "<|fa|>": 50300,
70
+ "<|fi|>": 50277,
71
+ "<|fo|>": 50338,
72
+ "<|fr|>": 50265,
73
+ "<|gl|>": 50319,
74
+ "<|gu|>": 50333,
75
+ "<|haw|>": 50352,
76
+ "<|ha|>": 50354,
77
+ "<|he|>": 50279,
78
+ "<|hi|>": 50276,
79
+ "<|hr|>": 50291,
80
+ "<|ht|>": 50339,
81
+ "<|hu|>": 50286,
82
+ "<|hy|>": 50312,
83
+ "<|id|>": 50275,
84
+ "<|is|>": 50311,
85
+ "<|it|>": 50274,
86
+ "<|ja|>": 50266,
87
+ "<|jw|>": 50356,
88
+ "<|ka|>": 50329,
89
+ "<|kk|>": 50316,
90
+ "<|km|>": 50323,
91
+ "<|kn|>": 50306,
92
+ "<|ko|>": 50264,
93
+ "<|la|>": 50294,
94
+ "<|lb|>": 50345,
95
+ "<|ln|>": 50353,
96
+ "<|lo|>": 50336,
97
+ "<|lt|>": 50293,
98
+ "<|lv|>": 50301,
99
+ "<|mg|>": 50349,
100
+ "<|mi|>": 50295,
101
+ "<|mk|>": 50308,
102
+ "<|ml|>": 50296,
103
+ "<|mn|>": 50314,
104
+ "<|mr|>": 50320,
105
+ "<|ms|>": 50282,
106
+ "<|mt|>": 50343,
107
+ "<|my|>": 50346,
108
+ "<|ne|>": 50313,
109
+ "<|nl|>": 50271,
110
+ "<|nn|>": 50342,
111
+ "<|no|>": 50288,
112
+ "<|oc|>": 50328,
113
+ "<|pa|>": 50321,
114
+ "<|pl|>": 50269,
115
+ "<|ps|>": 50340,
116
+ "<|pt|>": 50267,
117
+ "<|ro|>": 50284,
118
+ "<|ru|>": 50263,
119
+ "<|sa|>": 50344,
120
+ "<|sd|>": 50332,
121
+ "<|si|>": 50322,
122
+ "<|sk|>": 50298,
123
+ "<|sl|>": 50305,
124
+ "<|sn|>": 50324,
125
+ "<|so|>": 50326,
126
+ "<|sq|>": 50317,
127
+ "<|sr|>": 50303,
128
+ "<|su|>": 50357,
129
+ "<|sv|>": 50273,
130
+ "<|sw|>": 50318,
131
+ "<|ta|>": 50287,
132
+ "<|te|>": 50299,
133
+ "<|tg|>": 50331,
134
+ "<|th|>": 50289,
135
+ "<|tk|>": 50341,
136
+ "<|tl|>": 50348,
137
+ "<|tr|>": 50268,
138
+ "<|tt|>": 50351,
139
+ "<|uk|>": 50280,
140
+ "<|ur|>": 50290,
141
+ "<|uz|>": 50337,
142
+ "<|vi|>": 50278,
143
+ "<|yi|>": 50335,
144
+ "<|yo|>": 50325,
145
+ "<|zh|>": 50260
146
+ },
147
+ "language": "hindi",
148
+ "length_penalty": 1.0,
149
+ "max_initial_timestamp_index": 50,
150
+ "max_length": 448,
151
+ "min_length": 0,
152
+ "no_repeat_ngram_size": 0,
153
+ "no_timestamps_token_id": 50363,
154
+ "num_assistant_tokens": 20,
155
+ "num_assistant_tokens_schedule": "constant",
156
+ "num_beam_groups": 1,
157
+ "num_beams": 1,
158
+ "num_return_sequences": 1,
159
+ "output_scores": false,
160
+ "pad_token_id": 50257,
161
+ "prev_sot_token_id": 50361,
162
+ "remove_invalid_values": false,
163
+ "repetition_penalty": 1.0,
164
+ "return_dict_in_generate": false,
165
+ "return_timestamps": false,
166
+ "suppress_tokens": [
167
+ 1,
168
+ 2,
169
+ 7,
170
+ 8,
171
+ 9,
172
+ 10,
173
+ 14,
174
+ 25,
175
+ 26,
176
+ 27,
177
+ 28,
178
+ 29,
179
+ 31,
180
+ 58,
181
+ 59,
182
+ 60,
183
+ 61,
184
+ 62,
185
+ 63,
186
+ 90,
187
+ 91,
188
+ 92,
189
+ 93,
190
+ 359,
191
+ 503,
192
+ 522,
193
+ 542,
194
+ 873,
195
+ 893,
196
+ 902,
197
+ 918,
198
+ 922,
199
+ 931,
200
+ 1350,
201
+ 1853,
202
+ 1982,
203
+ 2460,
204
+ 2627,
205
+ 3246,
206
+ 3253,
207
+ 3268,
208
+ 3536,
209
+ 3846,
210
+ 3961,
211
+ 4183,
212
+ 4667,
213
+ 6585,
214
+ 6647,
215
+ 7273,
216
+ 9061,
217
+ 9383,
218
+ 10428,
219
+ 10929,
220
+ 11938,
221
+ 12033,
222
+ 12331,
223
+ 12562,
224
+ 13793,
225
+ 14157,
226
+ 14635,
227
+ 15265,
228
+ 15618,
229
+ 16553,
230
+ 16604,
231
+ 18362,
232
+ 18956,
233
+ 20075,
234
+ 21675,
235
+ 22520,
236
+ 26130,
237
+ 26161,
238
+ 26435,
239
+ 28279,
240
+ 29464,
241
+ 31650,
242
+ 32302,
243
+ 32470,
244
+ 36865,
245
+ 42863,
246
+ 47425,
247
+ 49870,
248
+ 50254,
249
+ 50258,
250
+ 50358,
251
+ 50359,
252
+ 50360,
253
+ 50361,
254
+ 50362
255
+ ],
256
+ "target_lookbehind": 10,
257
+ "task": "transcribe",
258
+ "task_to_id": {
259
+ "transcribe": 50359,
260
+ "translate": 50358
261
+ },
262
+ "temperature": 1.0,
263
+ "top_k": 50,
264
+ "top_p": 1.0,
265
+ "transformers_version": "5.3.0",
266
+ "typical_p": 1.0,
267
+ "use_cache": true
268
+ }
checkpoint-1000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dde2332794e7035788c6811f1cce179578b0fe7566c7e5f997a005d07984a24d
3
+ size 151061672
checkpoint-1000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0d8e969043fe15a3d5842bb8589325eff0bf2e58687cd2cbeb14170986b7e8cf
3
+ size 302227787
checkpoint-1000/preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 80,
6
+ "hop_length": 160,
7
+ "n_fft": 400,
8
+ "n_samples": 480000,
9
+ "nb_max_frames": 3000,
10
+ "padding_side": "right",
11
+ "padding_value": 0.0,
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
checkpoint-1000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92122a272ffea4d679bdd84ad5873f2bd72364515d1b7b93e08d7c44a5d070bb
3
+ size 14709
checkpoint-1000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cd70d88bdc41f5fba90d8298ab252d7406f5e25f3b0321970ff58f29c019af5
3
+ size 1383
checkpoint-1000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:323376ec23183398450433e2d5d0f527a24bfa1bbddc8d77c78a0c8e235a54a4
3
+ size 1465
checkpoint-1000/trainer_state.json ADDED
@@ -0,0 +1,332 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1000,
3
+ "best_metric": 64.67617349970291,
4
+ "best_model_checkpoint": "./whisper-tiny-maithili/checkpoint-1000",
5
+ "epoch": 6.850771869639794,
6
+ "eval_steps": 500,
7
+ "global_step": 1000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.17152658662092624,
14
+ "grad_norm": 18.268054962158203,
15
+ "learning_rate": 1.2000000000000002e-06,
16
+ "loss": 9.723193969726562,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.34305317324185247,
21
+ "grad_norm": 13.877284049987793,
22
+ "learning_rate": 2.4500000000000003e-06,
23
+ "loss": 8.318059692382812,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.5145797598627787,
28
+ "grad_norm": 11.479126930236816,
29
+ "learning_rate": 3.7e-06,
30
+ "loss": 6.970803833007812,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.6861063464837049,
35
+ "grad_norm": 10.104531288146973,
36
+ "learning_rate": 4.95e-06,
37
+ "loss": 5.796900634765625,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.8576329331046312,
42
+ "grad_norm": 10.247244834899902,
43
+ "learning_rate": 6.200000000000001e-06,
44
+ "loss": 4.848861389160156,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 1.0274442538593482,
49
+ "grad_norm": 7.673226356506348,
50
+ "learning_rate": 7.450000000000001e-06,
51
+ "loss": 3.985304870605469,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 1.1989708404802744,
56
+ "grad_norm": 7.689826488494873,
57
+ "learning_rate": 8.700000000000001e-06,
58
+ "loss": 3.524297180175781,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 1.3704974271012007,
63
+ "grad_norm": 8.599395751953125,
64
+ "learning_rate": 9.950000000000001e-06,
65
+ "loss": 3.220665283203125,
66
+ "step": 200
67
+ },
68
+ {
69
+ "epoch": 1.542024013722127,
70
+ "grad_norm": 8.532909393310547,
71
+ "learning_rate": 9.866666666666668e-06,
72
+ "loss": 3.0051885986328126,
73
+ "step": 225
74
+ },
75
+ {
76
+ "epoch": 1.7135506003430532,
77
+ "grad_norm": 8.584299087524414,
78
+ "learning_rate": 9.727777777777777e-06,
79
+ "loss": 2.7648504638671874,
80
+ "step": 250
81
+ },
82
+ {
83
+ "epoch": 1.8850771869639793,
84
+ "grad_norm": 8.186919212341309,
85
+ "learning_rate": 9.58888888888889e-06,
86
+ "loss": 2.6434637451171876,
87
+ "step": 275
88
+ },
89
+ {
90
+ "epoch": 2.0548885077186965,
91
+ "grad_norm": 7.06594181060791,
92
+ "learning_rate": 9.450000000000001e-06,
93
+ "loss": 2.485320739746094,
94
+ "step": 300
95
+ },
96
+ {
97
+ "epoch": 2.2264150943396226,
98
+ "grad_norm": 7.2849907875061035,
99
+ "learning_rate": 9.311111111111112e-06,
100
+ "loss": 2.2979925537109374,
101
+ "step": 325
102
+ },
103
+ {
104
+ "epoch": 2.3979416809605487,
105
+ "grad_norm": 7.386153221130371,
106
+ "learning_rate": 9.172222222222223e-06,
107
+ "loss": 2.249031982421875,
108
+ "step": 350
109
+ },
110
+ {
111
+ "epoch": 2.5694682675814753,
112
+ "grad_norm": 8.004015922546387,
113
+ "learning_rate": 9.033333333333334e-06,
114
+ "loss": 2.181380310058594,
115
+ "step": 375
116
+ },
117
+ {
118
+ "epoch": 2.7409948542024014,
119
+ "grad_norm": 6.979090213775635,
120
+ "learning_rate": 8.894444444444445e-06,
121
+ "loss": 2.1656195068359376,
122
+ "step": 400
123
+ },
124
+ {
125
+ "epoch": 2.9125214408233275,
126
+ "grad_norm": 6.589767932891846,
127
+ "learning_rate": 8.755555555555556e-06,
128
+ "loss": 2.2088014221191408,
129
+ "step": 425
130
+ },
131
+ {
132
+ "epoch": 3.0823327615780447,
133
+ "grad_norm": 8.118329048156738,
134
+ "learning_rate": 8.616666666666668e-06,
135
+ "loss": 2.0147331237792967,
136
+ "step": 450
137
+ },
138
+ {
139
+ "epoch": 3.253859348198971,
140
+ "grad_norm": 7.051534652709961,
141
+ "learning_rate": 8.477777777777778e-06,
142
+ "loss": 1.896328887939453,
143
+ "step": 475
144
+ },
145
+ {
146
+ "epoch": 3.425385934819897,
147
+ "grad_norm": 6.275884628295898,
148
+ "learning_rate": 8.33888888888889e-06,
149
+ "loss": 1.886772918701172,
150
+ "step": 500
151
+ },
152
+ {
153
+ "epoch": 3.425385934819897,
154
+ "eval_loss": 0.5728768110275269,
155
+ "eval_runtime": 92.9426,
156
+ "eval_samples_per_second": 2.797,
157
+ "eval_steps_per_second": 0.699,
158
+ "eval_wer": 68.77599524658348,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 3.5969125214408235,
163
+ "grad_norm": 7.222710609436035,
164
+ "learning_rate": 8.2e-06,
165
+ "loss": 1.8691773986816407,
166
+ "step": 525
167
+ },
168
+ {
169
+ "epoch": 3.7684391080617496,
170
+ "grad_norm": 6.063198566436768,
171
+ "learning_rate": 8.061111111111112e-06,
172
+ "loss": 1.8207814025878906,
173
+ "step": 550
174
+ },
175
+ {
176
+ "epoch": 3.9399656946826758,
177
+ "grad_norm": 6.641396522521973,
178
+ "learning_rate": 7.922222222222223e-06,
179
+ "loss": 1.7857606506347656,
180
+ "step": 575
181
+ },
182
+ {
183
+ "epoch": 4.109777015437393,
184
+ "grad_norm": 6.6834397315979,
185
+ "learning_rate": 7.783333333333334e-06,
186
+ "loss": 1.713679656982422,
187
+ "step": 600
188
+ },
189
+ {
190
+ "epoch": 4.281303602058319,
191
+ "grad_norm": 6.873757362365723,
192
+ "learning_rate": 7.644444444444445e-06,
193
+ "loss": 1.6278848266601562,
194
+ "step": 625
195
+ },
196
+ {
197
+ "epoch": 4.452830188679245,
198
+ "grad_norm": 6.53254508972168,
199
+ "learning_rate": 7.505555555555556e-06,
200
+ "loss": 1.5813905334472655,
201
+ "step": 650
202
+ },
203
+ {
204
+ "epoch": 4.624356775300171,
205
+ "grad_norm": 7.650671482086182,
206
+ "learning_rate": 7.3666666666666676e-06,
207
+ "loss": 1.6567597961425782,
208
+ "step": 675
209
+ },
210
+ {
211
+ "epoch": 4.795883361921097,
212
+ "grad_norm": 6.784526348114014,
213
+ "learning_rate": 7.227777777777778e-06,
214
+ "loss": 1.6283486938476563,
215
+ "step": 700
216
+ },
217
+ {
218
+ "epoch": 4.967409948542024,
219
+ "grad_norm": 7.425609588623047,
220
+ "learning_rate": 7.0888888888888894e-06,
221
+ "loss": 1.580086669921875,
222
+ "step": 725
223
+ },
224
+ {
225
+ "epoch": 5.137221269296741,
226
+ "grad_norm": 7.560032367706299,
227
+ "learning_rate": 6.95e-06,
228
+ "loss": 1.4196165466308595,
229
+ "step": 750
230
+ },
231
+ {
232
+ "epoch": 5.308747855917667,
233
+ "grad_norm": 7.114623069763184,
234
+ "learning_rate": 6.811111111111111e-06,
235
+ "loss": 1.4393228149414063,
236
+ "step": 775
237
+ },
238
+ {
239
+ "epoch": 5.480274442538594,
240
+ "grad_norm": 6.174019813537598,
241
+ "learning_rate": 6.672222222222223e-06,
242
+ "loss": 1.4180364990234375,
243
+ "step": 800
244
+ },
245
+ {
246
+ "epoch": 5.65180102915952,
247
+ "grad_norm": 6.444286346435547,
248
+ "learning_rate": 6.533333333333334e-06,
249
+ "loss": 1.4367037963867189,
250
+ "step": 825
251
+ },
252
+ {
253
+ "epoch": 5.823327615780446,
254
+ "grad_norm": 6.457458019256592,
255
+ "learning_rate": 6.394444444444445e-06,
256
+ "loss": 1.4541001892089844,
257
+ "step": 850
258
+ },
259
+ {
260
+ "epoch": 5.994854202401372,
261
+ "grad_norm": 6.65748929977417,
262
+ "learning_rate": 6.255555555555556e-06,
263
+ "loss": 1.4775286865234376,
264
+ "step": 875
265
+ },
266
+ {
267
+ "epoch": 6.164665523156089,
268
+ "grad_norm": 6.2816057205200195,
269
+ "learning_rate": 6.116666666666668e-06,
270
+ "loss": 1.2730085754394531,
271
+ "step": 900
272
+ },
273
+ {
274
+ "epoch": 6.3361921097770155,
275
+ "grad_norm": 6.40878963470459,
276
+ "learning_rate": 5.977777777777778e-06,
277
+ "loss": 1.2837075805664062,
278
+ "step": 925
279
+ },
280
+ {
281
+ "epoch": 6.507718696397942,
282
+ "grad_norm": 6.427629470825195,
283
+ "learning_rate": 5.8388888888888895e-06,
284
+ "loss": 1.2479456329345704,
285
+ "step": 950
286
+ },
287
+ {
288
+ "epoch": 6.679245283018868,
289
+ "grad_norm": 5.938961982727051,
290
+ "learning_rate": 5.7e-06,
291
+ "loss": 1.3641961669921876,
292
+ "step": 975
293
+ },
294
+ {
295
+ "epoch": 6.850771869639794,
296
+ "grad_norm": 6.981799125671387,
297
+ "learning_rate": 5.561111111111111e-06,
298
+ "loss": 1.2829299926757813,
299
+ "step": 1000
300
+ },
301
+ {
302
+ "epoch": 6.850771869639794,
303
+ "eval_loss": 0.5365099906921387,
304
+ "eval_runtime": 92.6416,
305
+ "eval_samples_per_second": 2.807,
306
+ "eval_steps_per_second": 0.702,
307
+ "eval_wer": 64.67617349970291,
308
+ "step": 1000
309
+ }
310
+ ],
311
+ "logging_steps": 25,
312
+ "max_steps": 2000,
313
+ "num_input_tokens_seen": 0,
314
+ "num_train_epochs": 14,
315
+ "save_steps": 500,
316
+ "stateful_callbacks": {
317
+ "TrainerControl": {
318
+ "args": {
319
+ "should_epoch_stop": false,
320
+ "should_evaluate": false,
321
+ "should_log": false,
322
+ "should_save": true,
323
+ "should_training_stop": false
324
+ },
325
+ "attributes": {}
326
+ }
327
+ },
328
+ "total_flos": 3.9331130867712e+17,
329
+ "train_batch_size": 4,
330
+ "trial_name": null,
331
+ "trial_params": null
332
+ }
checkpoint-1000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d3768d5597d6e5a7d63118e80f44059101c56bf60f8f4722ac7e1bcfe7d31f
3
+ size 5329
checkpoint-1500/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 50257,
10
+ "classifier_proj_size": 256,
11
+ "d_model": 384,
12
+ "decoder_attention_heads": 6,
13
+ "decoder_ffn_dim": 1536,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 4,
16
+ "decoder_start_token_id": 50258,
17
+ "dropout": 0.0,
18
+ "dtype": "float32",
19
+ "encoder_attention_heads": 6,
20
+ "encoder_ffn_dim": 1536,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 4,
23
+ "eos_token_id": 50257,
24
+ "forced_decoder_ids": [
25
+ [
26
+ 1,
27
+ 50259
28
+ ],
29
+ [
30
+ 2,
31
+ 50359
32
+ ],
33
+ [
34
+ 3,
35
+ 50363
36
+ ]
37
+ ],
38
+ "init_std": 0.02,
39
+ "is_encoder_decoder": true,
40
+ "mask_feature_length": 10,
41
+ "mask_feature_min_masks": 0,
42
+ "mask_feature_prob": 0.0,
43
+ "mask_time_length": 10,
44
+ "mask_time_min_masks": 2,
45
+ "mask_time_prob": 0.05,
46
+ "max_source_positions": 1500,
47
+ "max_target_positions": 448,
48
+ "median_filter_width": 7,
49
+ "model_type": "whisper",
50
+ "num_hidden_layers": 4,
51
+ "num_mel_bins": 80,
52
+ "pad_token_id": 50257,
53
+ "scale_embedding": false,
54
+ "tie_word_embeddings": true,
55
+ "transformers_version": "5.3.0",
56
+ "use_cache": false,
57
+ "use_weighted_layer_sum": false,
58
+ "vocab_size": 51865
59
+ }
checkpoint-1500/generation_config.json ADDED
@@ -0,0 +1,268 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 2
6
+ ],
7
+ [
8
+ 3,
9
+ 0
10
+ ],
11
+ [
12
+ 3,
13
+ 2
14
+ ],
15
+ [
16
+ 3,
17
+ 3
18
+ ],
19
+ [
20
+ 3,
21
+ 4
22
+ ],
23
+ [
24
+ 3,
25
+ 5
26
+ ]
27
+ ],
28
+ "assistant_confidence_threshold": 0.4,
29
+ "assistant_lookbehind": 10,
30
+ "begin_suppress_tokens": [
31
+ 220,
32
+ 50257
33
+ ],
34
+ "bos_token_id": 50257,
35
+ "decoder_start_token_id": 50258,
36
+ "diversity_penalty": 0.0,
37
+ "do_sample": false,
38
+ "early_stopping": false,
39
+ "encoder_no_repeat_ngram_size": 0,
40
+ "encoder_repetition_penalty": 1.0,
41
+ "eos_token_id": 50257,
42
+ "epsilon_cutoff": 0.0,
43
+ "eta_cutoff": 0.0,
44
+ "forced_decoder_ids": null,
45
+ "is_multilingual": true,
46
+ "lang_to_id": {
47
+ "<|af|>": 50327,
48
+ "<|am|>": 50334,
49
+ "<|ar|>": 50272,
50
+ "<|as|>": 50350,
51
+ "<|az|>": 50304,
52
+ "<|ba|>": 50355,
53
+ "<|be|>": 50330,
54
+ "<|bg|>": 50292,
55
+ "<|bn|>": 50302,
56
+ "<|bo|>": 50347,
57
+ "<|br|>": 50309,
58
+ "<|bs|>": 50315,
59
+ "<|ca|>": 50270,
60
+ "<|cs|>": 50283,
61
+ "<|cy|>": 50297,
62
+ "<|da|>": 50285,
63
+ "<|de|>": 50261,
64
+ "<|el|>": 50281,
65
+ "<|en|>": 50259,
66
+ "<|es|>": 50262,
67
+ "<|et|>": 50307,
68
+ "<|eu|>": 50310,
69
+ "<|fa|>": 50300,
70
+ "<|fi|>": 50277,
71
+ "<|fo|>": 50338,
72
+ "<|fr|>": 50265,
73
+ "<|gl|>": 50319,
74
+ "<|gu|>": 50333,
75
+ "<|haw|>": 50352,
76
+ "<|ha|>": 50354,
77
+ "<|he|>": 50279,
78
+ "<|hi|>": 50276,
79
+ "<|hr|>": 50291,
80
+ "<|ht|>": 50339,
81
+ "<|hu|>": 50286,
82
+ "<|hy|>": 50312,
83
+ "<|id|>": 50275,
84
+ "<|is|>": 50311,
85
+ "<|it|>": 50274,
86
+ "<|ja|>": 50266,
87
+ "<|jw|>": 50356,
88
+ "<|ka|>": 50329,
89
+ "<|kk|>": 50316,
90
+ "<|km|>": 50323,
91
+ "<|kn|>": 50306,
92
+ "<|ko|>": 50264,
93
+ "<|la|>": 50294,
94
+ "<|lb|>": 50345,
95
+ "<|ln|>": 50353,
96
+ "<|lo|>": 50336,
97
+ "<|lt|>": 50293,
98
+ "<|lv|>": 50301,
99
+ "<|mg|>": 50349,
100
+ "<|mi|>": 50295,
101
+ "<|mk|>": 50308,
102
+ "<|ml|>": 50296,
103
+ "<|mn|>": 50314,
104
+ "<|mr|>": 50320,
105
+ "<|ms|>": 50282,
106
+ "<|mt|>": 50343,
107
+ "<|my|>": 50346,
108
+ "<|ne|>": 50313,
109
+ "<|nl|>": 50271,
110
+ "<|nn|>": 50342,
111
+ "<|no|>": 50288,
112
+ "<|oc|>": 50328,
113
+ "<|pa|>": 50321,
114
+ "<|pl|>": 50269,
115
+ "<|ps|>": 50340,
116
+ "<|pt|>": 50267,
117
+ "<|ro|>": 50284,
118
+ "<|ru|>": 50263,
119
+ "<|sa|>": 50344,
120
+ "<|sd|>": 50332,
121
+ "<|si|>": 50322,
122
+ "<|sk|>": 50298,
123
+ "<|sl|>": 50305,
124
+ "<|sn|>": 50324,
125
+ "<|so|>": 50326,
126
+ "<|sq|>": 50317,
127
+ "<|sr|>": 50303,
128
+ "<|su|>": 50357,
129
+ "<|sv|>": 50273,
130
+ "<|sw|>": 50318,
131
+ "<|ta|>": 50287,
132
+ "<|te|>": 50299,
133
+ "<|tg|>": 50331,
134
+ "<|th|>": 50289,
135
+ "<|tk|>": 50341,
136
+ "<|tl|>": 50348,
137
+ "<|tr|>": 50268,
138
+ "<|tt|>": 50351,
139
+ "<|uk|>": 50280,
140
+ "<|ur|>": 50290,
141
+ "<|uz|>": 50337,
142
+ "<|vi|>": 50278,
143
+ "<|yi|>": 50335,
144
+ "<|yo|>": 50325,
145
+ "<|zh|>": 50260
146
+ },
147
+ "language": "hindi",
148
+ "length_penalty": 1.0,
149
+ "max_initial_timestamp_index": 50,
150
+ "max_length": 448,
151
+ "min_length": 0,
152
+ "no_repeat_ngram_size": 0,
153
+ "no_timestamps_token_id": 50363,
154
+ "num_assistant_tokens": 20,
155
+ "num_assistant_tokens_schedule": "constant",
156
+ "num_beam_groups": 1,
157
+ "num_beams": 1,
158
+ "num_return_sequences": 1,
159
+ "output_scores": false,
160
+ "pad_token_id": 50257,
161
+ "prev_sot_token_id": 50361,
162
+ "remove_invalid_values": false,
163
+ "repetition_penalty": 1.0,
164
+ "return_dict_in_generate": false,
165
+ "return_timestamps": false,
166
+ "suppress_tokens": [
167
+ 1,
168
+ 2,
169
+ 7,
170
+ 8,
171
+ 9,
172
+ 10,
173
+ 14,
174
+ 25,
175
+ 26,
176
+ 27,
177
+ 28,
178
+ 29,
179
+ 31,
180
+ 58,
181
+ 59,
182
+ 60,
183
+ 61,
184
+ 62,
185
+ 63,
186
+ 90,
187
+ 91,
188
+ 92,
189
+ 93,
190
+ 359,
191
+ 503,
192
+ 522,
193
+ 542,
194
+ 873,
195
+ 893,
196
+ 902,
197
+ 918,
198
+ 922,
199
+ 931,
200
+ 1350,
201
+ 1853,
202
+ 1982,
203
+ 2460,
204
+ 2627,
205
+ 3246,
206
+ 3253,
207
+ 3268,
208
+ 3536,
209
+ 3846,
210
+ 3961,
211
+ 4183,
212
+ 4667,
213
+ 6585,
214
+ 6647,
215
+ 7273,
216
+ 9061,
217
+ 9383,
218
+ 10428,
219
+ 10929,
220
+ 11938,
221
+ 12033,
222
+ 12331,
223
+ 12562,
224
+ 13793,
225
+ 14157,
226
+ 14635,
227
+ 15265,
228
+ 15618,
229
+ 16553,
230
+ 16604,
231
+ 18362,
232
+ 18956,
233
+ 20075,
234
+ 21675,
235
+ 22520,
236
+ 26130,
237
+ 26161,
238
+ 26435,
239
+ 28279,
240
+ 29464,
241
+ 31650,
242
+ 32302,
243
+ 32470,
244
+ 36865,
245
+ 42863,
246
+ 47425,
247
+ 49870,
248
+ 50254,
249
+ 50258,
250
+ 50358,
251
+ 50359,
252
+ 50360,
253
+ 50361,
254
+ 50362
255
+ ],
256
+ "target_lookbehind": 10,
257
+ "task": "transcribe",
258
+ "task_to_id": {
259
+ "transcribe": 50359,
260
+ "translate": 50358
261
+ },
262
+ "temperature": 1.0,
263
+ "top_k": 50,
264
+ "top_p": 1.0,
265
+ "transformers_version": "5.3.0",
266
+ "typical_p": 1.0,
267
+ "use_cache": true
268
+ }
checkpoint-1500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e7ff135784b97a6359df6fdb7340a678e6b376be4f04c331dd52ad2197083dd
3
+ size 151061672
checkpoint-1500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3dbc0288ae74973159c2624849d23c783b1f588b72e51a4c5eeb996809e156d5
3
+ size 302227787
checkpoint-1500/preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 80,
6
+ "hop_length": 160,
7
+ "n_fft": 400,
8
+ "n_samples": 480000,
9
+ "nb_max_frames": 3000,
10
+ "padding_side": "right",
11
+ "padding_value": 0.0,
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
checkpoint-1500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0743b8c1b4b14c1dfad74b815e091ac8f5be2806f75ae94d524060cf53de1d0d
3
+ size 14709
checkpoint-1500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97d4c1282b62c87a0147cb7e3ce2219debf7f8c5c7cd9ec6504d850e2b4ad23f
3
+ size 1383
checkpoint-1500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b0f814b8850b6448ece6ff7cb16df4071563e2f5d5083bb90477f4f457e7cfde
3
+ size 1465
checkpoint-1500/trainer_state.json ADDED
@@ -0,0 +1,481 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1500,
3
+ "best_metric": 63.903743315508024,
4
+ "best_model_checkpoint": "./whisper-tiny-maithili/checkpoint-1500",
5
+ "epoch": 10.274442538593481,
6
+ "eval_steps": 500,
7
+ "global_step": 1500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.17152658662092624,
14
+ "grad_norm": 18.268054962158203,
15
+ "learning_rate": 1.2000000000000002e-06,
16
+ "loss": 9.723193969726562,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.34305317324185247,
21
+ "grad_norm": 13.877284049987793,
22
+ "learning_rate": 2.4500000000000003e-06,
23
+ "loss": 8.318059692382812,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.5145797598627787,
28
+ "grad_norm": 11.479126930236816,
29
+ "learning_rate": 3.7e-06,
30
+ "loss": 6.970803833007812,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.6861063464837049,
35
+ "grad_norm": 10.104531288146973,
36
+ "learning_rate": 4.95e-06,
37
+ "loss": 5.796900634765625,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.8576329331046312,
42
+ "grad_norm": 10.247244834899902,
43
+ "learning_rate": 6.200000000000001e-06,
44
+ "loss": 4.848861389160156,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 1.0274442538593482,
49
+ "grad_norm": 7.673226356506348,
50
+ "learning_rate": 7.450000000000001e-06,
51
+ "loss": 3.985304870605469,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 1.1989708404802744,
56
+ "grad_norm": 7.689826488494873,
57
+ "learning_rate": 8.700000000000001e-06,
58
+ "loss": 3.524297180175781,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 1.3704974271012007,
63
+ "grad_norm": 8.599395751953125,
64
+ "learning_rate": 9.950000000000001e-06,
65
+ "loss": 3.220665283203125,
66
+ "step": 200
67
+ },
68
+ {
69
+ "epoch": 1.542024013722127,
70
+ "grad_norm": 8.532909393310547,
71
+ "learning_rate": 9.866666666666668e-06,
72
+ "loss": 3.0051885986328126,
73
+ "step": 225
74
+ },
75
+ {
76
+ "epoch": 1.7135506003430532,
77
+ "grad_norm": 8.584299087524414,
78
+ "learning_rate": 9.727777777777777e-06,
79
+ "loss": 2.7648504638671874,
80
+ "step": 250
81
+ },
82
+ {
83
+ "epoch": 1.8850771869639793,
84
+ "grad_norm": 8.186919212341309,
85
+ "learning_rate": 9.58888888888889e-06,
86
+ "loss": 2.6434637451171876,
87
+ "step": 275
88
+ },
89
+ {
90
+ "epoch": 2.0548885077186965,
91
+ "grad_norm": 7.06594181060791,
92
+ "learning_rate": 9.450000000000001e-06,
93
+ "loss": 2.485320739746094,
94
+ "step": 300
95
+ },
96
+ {
97
+ "epoch": 2.2264150943396226,
98
+ "grad_norm": 7.2849907875061035,
99
+ "learning_rate": 9.311111111111112e-06,
100
+ "loss": 2.2979925537109374,
101
+ "step": 325
102
+ },
103
+ {
104
+ "epoch": 2.3979416809605487,
105
+ "grad_norm": 7.386153221130371,
106
+ "learning_rate": 9.172222222222223e-06,
107
+ "loss": 2.249031982421875,
108
+ "step": 350
109
+ },
110
+ {
111
+ "epoch": 2.5694682675814753,
112
+ "grad_norm": 8.004015922546387,
113
+ "learning_rate": 9.033333333333334e-06,
114
+ "loss": 2.181380310058594,
115
+ "step": 375
116
+ },
117
+ {
118
+ "epoch": 2.7409948542024014,
119
+ "grad_norm": 6.979090213775635,
120
+ "learning_rate": 8.894444444444445e-06,
121
+ "loss": 2.1656195068359376,
122
+ "step": 400
123
+ },
124
+ {
125
+ "epoch": 2.9125214408233275,
126
+ "grad_norm": 6.589767932891846,
127
+ "learning_rate": 8.755555555555556e-06,
128
+ "loss": 2.2088014221191408,
129
+ "step": 425
130
+ },
131
+ {
132
+ "epoch": 3.0823327615780447,
133
+ "grad_norm": 8.118329048156738,
134
+ "learning_rate": 8.616666666666668e-06,
135
+ "loss": 2.0147331237792967,
136
+ "step": 450
137
+ },
138
+ {
139
+ "epoch": 3.253859348198971,
140
+ "grad_norm": 7.051534652709961,
141
+ "learning_rate": 8.477777777777778e-06,
142
+ "loss": 1.896328887939453,
143
+ "step": 475
144
+ },
145
+ {
146
+ "epoch": 3.425385934819897,
147
+ "grad_norm": 6.275884628295898,
148
+ "learning_rate": 8.33888888888889e-06,
149
+ "loss": 1.886772918701172,
150
+ "step": 500
151
+ },
152
+ {
153
+ "epoch": 3.425385934819897,
154
+ "eval_loss": 0.5728768110275269,
155
+ "eval_runtime": 92.9426,
156
+ "eval_samples_per_second": 2.797,
157
+ "eval_steps_per_second": 0.699,
158
+ "eval_wer": 68.77599524658348,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 3.5969125214408235,
163
+ "grad_norm": 7.222710609436035,
164
+ "learning_rate": 8.2e-06,
165
+ "loss": 1.8691773986816407,
166
+ "step": 525
167
+ },
168
+ {
169
+ "epoch": 3.7684391080617496,
170
+ "grad_norm": 6.063198566436768,
171
+ "learning_rate": 8.061111111111112e-06,
172
+ "loss": 1.8207814025878906,
173
+ "step": 550
174
+ },
175
+ {
176
+ "epoch": 3.9399656946826758,
177
+ "grad_norm": 6.641396522521973,
178
+ "learning_rate": 7.922222222222223e-06,
179
+ "loss": 1.7857606506347656,
180
+ "step": 575
181
+ },
182
+ {
183
+ "epoch": 4.109777015437393,
184
+ "grad_norm": 6.6834397315979,
185
+ "learning_rate": 7.783333333333334e-06,
186
+ "loss": 1.713679656982422,
187
+ "step": 600
188
+ },
189
+ {
190
+ "epoch": 4.281303602058319,
191
+ "grad_norm": 6.873757362365723,
192
+ "learning_rate": 7.644444444444445e-06,
193
+ "loss": 1.6278848266601562,
194
+ "step": 625
195
+ },
196
+ {
197
+ "epoch": 4.452830188679245,
198
+ "grad_norm": 6.53254508972168,
199
+ "learning_rate": 7.505555555555556e-06,
200
+ "loss": 1.5813905334472655,
201
+ "step": 650
202
+ },
203
+ {
204
+ "epoch": 4.624356775300171,
205
+ "grad_norm": 7.650671482086182,
206
+ "learning_rate": 7.3666666666666676e-06,
207
+ "loss": 1.6567597961425782,
208
+ "step": 675
209
+ },
210
+ {
211
+ "epoch": 4.795883361921097,
212
+ "grad_norm": 6.784526348114014,
213
+ "learning_rate": 7.227777777777778e-06,
214
+ "loss": 1.6283486938476563,
215
+ "step": 700
216
+ },
217
+ {
218
+ "epoch": 4.967409948542024,
219
+ "grad_norm": 7.425609588623047,
220
+ "learning_rate": 7.0888888888888894e-06,
221
+ "loss": 1.580086669921875,
222
+ "step": 725
223
+ },
224
+ {
225
+ "epoch": 5.137221269296741,
226
+ "grad_norm": 7.560032367706299,
227
+ "learning_rate": 6.95e-06,
228
+ "loss": 1.4196165466308595,
229
+ "step": 750
230
+ },
231
+ {
232
+ "epoch": 5.308747855917667,
233
+ "grad_norm": 7.114623069763184,
234
+ "learning_rate": 6.811111111111111e-06,
235
+ "loss": 1.4393228149414063,
236
+ "step": 775
237
+ },
238
+ {
239
+ "epoch": 5.480274442538594,
240
+ "grad_norm": 6.174019813537598,
241
+ "learning_rate": 6.672222222222223e-06,
242
+ "loss": 1.4180364990234375,
243
+ "step": 800
244
+ },
245
+ {
246
+ "epoch": 5.65180102915952,
247
+ "grad_norm": 6.444286346435547,
248
+ "learning_rate": 6.533333333333334e-06,
249
+ "loss": 1.4367037963867189,
250
+ "step": 825
251
+ },
252
+ {
253
+ "epoch": 5.823327615780446,
254
+ "grad_norm": 6.457458019256592,
255
+ "learning_rate": 6.394444444444445e-06,
256
+ "loss": 1.4541001892089844,
257
+ "step": 850
258
+ },
259
+ {
260
+ "epoch": 5.994854202401372,
261
+ "grad_norm": 6.65748929977417,
262
+ "learning_rate": 6.255555555555556e-06,
263
+ "loss": 1.4775286865234376,
264
+ "step": 875
265
+ },
266
+ {
267
+ "epoch": 6.164665523156089,
268
+ "grad_norm": 6.2816057205200195,
269
+ "learning_rate": 6.116666666666668e-06,
270
+ "loss": 1.2730085754394531,
271
+ "step": 900
272
+ },
273
+ {
274
+ "epoch": 6.3361921097770155,
275
+ "grad_norm": 6.40878963470459,
276
+ "learning_rate": 5.977777777777778e-06,
277
+ "loss": 1.2837075805664062,
278
+ "step": 925
279
+ },
280
+ {
281
+ "epoch": 6.507718696397942,
282
+ "grad_norm": 6.427629470825195,
283
+ "learning_rate": 5.8388888888888895e-06,
284
+ "loss": 1.2479456329345704,
285
+ "step": 950
286
+ },
287
+ {
288
+ "epoch": 6.679245283018868,
289
+ "grad_norm": 5.938961982727051,
290
+ "learning_rate": 5.7e-06,
291
+ "loss": 1.3641961669921876,
292
+ "step": 975
293
+ },
294
+ {
295
+ "epoch": 6.850771869639794,
296
+ "grad_norm": 6.981799125671387,
297
+ "learning_rate": 5.561111111111111e-06,
298
+ "loss": 1.2829299926757813,
299
+ "step": 1000
300
+ },
301
+ {
302
+ "epoch": 6.850771869639794,
303
+ "eval_loss": 0.5365099906921387,
304
+ "eval_runtime": 92.6416,
305
+ "eval_samples_per_second": 2.807,
306
+ "eval_steps_per_second": 0.702,
307
+ "eval_wer": 64.67617349970291,
308
+ "step": 1000
309
+ },
310
+ {
311
+ "epoch": 7.020583190394511,
312
+ "grad_norm": 6.462595462799072,
313
+ "learning_rate": 5.422222222222223e-06,
314
+ "loss": 1.266632080078125,
315
+ "step": 1025
316
+ },
317
+ {
318
+ "epoch": 7.192109777015437,
319
+ "grad_norm": 6.442847728729248,
320
+ "learning_rate": 5.283333333333333e-06,
321
+ "loss": 1.1616410827636718,
322
+ "step": 1050
323
+ },
324
+ {
325
+ "epoch": 7.363636363636363,
326
+ "grad_norm": 5.910035133361816,
327
+ "learning_rate": 5.144444444444445e-06,
328
+ "loss": 1.1423403167724608,
329
+ "step": 1075
330
+ },
331
+ {
332
+ "epoch": 7.535162950257289,
333
+ "grad_norm": 6.2111334800720215,
334
+ "learning_rate": 5.005555555555556e-06,
335
+ "loss": 1.1994317626953126,
336
+ "step": 1100
337
+ },
338
+ {
339
+ "epoch": 7.7066895368782165,
340
+ "grad_norm": 5.6760783195495605,
341
+ "learning_rate": 4.866666666666667e-06,
342
+ "loss": 1.1873680877685546,
343
+ "step": 1125
344
+ },
345
+ {
346
+ "epoch": 7.878216123499143,
347
+ "grad_norm": 6.996194839477539,
348
+ "learning_rate": 4.727777777777779e-06,
349
+ "loss": 1.1682706451416016,
350
+ "step": 1150
351
+ },
352
+ {
353
+ "epoch": 8.04802744425386,
354
+ "grad_norm": 5.388121604919434,
355
+ "learning_rate": 4.58888888888889e-06,
356
+ "loss": 1.1501982879638672,
357
+ "step": 1175
358
+ },
359
+ {
360
+ "epoch": 8.219554030874786,
361
+ "grad_norm": 6.324208736419678,
362
+ "learning_rate": 4.450000000000001e-06,
363
+ "loss": 1.0414784240722657,
364
+ "step": 1200
365
+ },
366
+ {
367
+ "epoch": 8.391080617495712,
368
+ "grad_norm": 6.224495887756348,
369
+ "learning_rate": 4.3111111111111115e-06,
370
+ "loss": 1.0576978302001954,
371
+ "step": 1225
372
+ },
373
+ {
374
+ "epoch": 8.562607204116638,
375
+ "grad_norm": 5.9399094581604,
376
+ "learning_rate": 4.1722222222222225e-06,
377
+ "loss": 1.0483750915527343,
378
+ "step": 1250
379
+ },
380
+ {
381
+ "epoch": 8.734133790737564,
382
+ "grad_norm": 6.331912994384766,
383
+ "learning_rate": 4.033333333333333e-06,
384
+ "loss": 1.0921112060546876,
385
+ "step": 1275
386
+ },
387
+ {
388
+ "epoch": 8.90566037735849,
389
+ "grad_norm": 7.319565296173096,
390
+ "learning_rate": 3.894444444444444e-06,
391
+ "loss": 1.0816537475585937,
392
+ "step": 1300
393
+ },
394
+ {
395
+ "epoch": 9.075471698113208,
396
+ "grad_norm": 6.406201362609863,
397
+ "learning_rate": 3.7555555555555557e-06,
398
+ "loss": 1.0307456207275392,
399
+ "step": 1325
400
+ },
401
+ {
402
+ "epoch": 9.246998284734135,
403
+ "grad_norm": 6.348610877990723,
404
+ "learning_rate": 3.616666666666667e-06,
405
+ "loss": 0.9632396697998047,
406
+ "step": 1350
407
+ },
408
+ {
409
+ "epoch": 9.41852487135506,
410
+ "grad_norm": 6.033849239349365,
411
+ "learning_rate": 3.4777777777777784e-06,
412
+ "loss": 0.9932768249511719,
413
+ "step": 1375
414
+ },
415
+ {
416
+ "epoch": 9.590051457975987,
417
+ "grad_norm": 6.423510551452637,
418
+ "learning_rate": 3.3388888888888893e-06,
419
+ "loss": 0.978936538696289,
420
+ "step": 1400
421
+ },
422
+ {
423
+ "epoch": 9.761578044596913,
424
+ "grad_norm": 5.581418514251709,
425
+ "learning_rate": 3.2000000000000003e-06,
426
+ "loss": 0.9529872894287109,
427
+ "step": 1425
428
+ },
429
+ {
430
+ "epoch": 9.933104631217839,
431
+ "grad_norm": 7.128633499145508,
432
+ "learning_rate": 3.0611111111111112e-06,
433
+ "loss": 1.00614990234375,
434
+ "step": 1450
435
+ },
436
+ {
437
+ "epoch": 10.102915951972555,
438
+ "grad_norm": 6.873051643371582,
439
+ "learning_rate": 2.9222222222222226e-06,
440
+ "loss": 0.9351605224609375,
441
+ "step": 1475
442
+ },
443
+ {
444
+ "epoch": 10.274442538593481,
445
+ "grad_norm": 6.594143390655518,
446
+ "learning_rate": 2.7833333333333335e-06,
447
+ "loss": 0.8834098815917969,
448
+ "step": 1500
449
+ },
450
+ {
451
+ "epoch": 10.274442538593481,
452
+ "eval_loss": 0.5569483637809753,
453
+ "eval_runtime": 93.3641,
454
+ "eval_samples_per_second": 2.785,
455
+ "eval_steps_per_second": 0.696,
456
+ "eval_wer": 63.903743315508024,
457
+ "step": 1500
458
+ }
459
+ ],
460
+ "logging_steps": 25,
461
+ "max_steps": 2000,
462
+ "num_input_tokens_seen": 0,
463
+ "num_train_epochs": 14,
464
+ "save_steps": 500,
465
+ "stateful_callbacks": {
466
+ "TrainerControl": {
467
+ "args": {
468
+ "should_epoch_stop": false,
469
+ "should_evaluate": false,
470
+ "should_log": false,
471
+ "should_save": true,
472
+ "should_training_stop": false
473
+ },
474
+ "attributes": {}
475
+ }
476
+ },
477
+ "total_flos": 5.898684874752e+17,
478
+ "train_batch_size": 4,
479
+ "trial_name": null,
480
+ "trial_params": null
481
+ }
checkpoint-1500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d3768d5597d6e5a7d63118e80f44059101c56bf60f8f4722ac7e1bcfe7d31f
3
+ size 5329
checkpoint-2000/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 50257,
10
+ "classifier_proj_size": 256,
11
+ "d_model": 384,
12
+ "decoder_attention_heads": 6,
13
+ "decoder_ffn_dim": 1536,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 4,
16
+ "decoder_start_token_id": 50258,
17
+ "dropout": 0.0,
18
+ "dtype": "float32",
19
+ "encoder_attention_heads": 6,
20
+ "encoder_ffn_dim": 1536,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 4,
23
+ "eos_token_id": 50257,
24
+ "forced_decoder_ids": [
25
+ [
26
+ 1,
27
+ 50259
28
+ ],
29
+ [
30
+ 2,
31
+ 50359
32
+ ],
33
+ [
34
+ 3,
35
+ 50363
36
+ ]
37
+ ],
38
+ "init_std": 0.02,
39
+ "is_encoder_decoder": true,
40
+ "mask_feature_length": 10,
41
+ "mask_feature_min_masks": 0,
42
+ "mask_feature_prob": 0.0,
43
+ "mask_time_length": 10,
44
+ "mask_time_min_masks": 2,
45
+ "mask_time_prob": 0.05,
46
+ "max_source_positions": 1500,
47
+ "max_target_positions": 448,
48
+ "median_filter_width": 7,
49
+ "model_type": "whisper",
50
+ "num_hidden_layers": 4,
51
+ "num_mel_bins": 80,
52
+ "pad_token_id": 50257,
53
+ "scale_embedding": false,
54
+ "tie_word_embeddings": true,
55
+ "transformers_version": "5.3.0",
56
+ "use_cache": false,
57
+ "use_weighted_layer_sum": false,
58
+ "vocab_size": 51865
59
+ }
checkpoint-2000/generation_config.json ADDED
@@ -0,0 +1,268 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 2
6
+ ],
7
+ [
8
+ 3,
9
+ 0
10
+ ],
11
+ [
12
+ 3,
13
+ 2
14
+ ],
15
+ [
16
+ 3,
17
+ 3
18
+ ],
19
+ [
20
+ 3,
21
+ 4
22
+ ],
23
+ [
24
+ 3,
25
+ 5
26
+ ]
27
+ ],
28
+ "assistant_confidence_threshold": 0.4,
29
+ "assistant_lookbehind": 10,
30
+ "begin_suppress_tokens": [
31
+ 220,
32
+ 50257
33
+ ],
34
+ "bos_token_id": 50257,
35
+ "decoder_start_token_id": 50258,
36
+ "diversity_penalty": 0.0,
37
+ "do_sample": false,
38
+ "early_stopping": false,
39
+ "encoder_no_repeat_ngram_size": 0,
40
+ "encoder_repetition_penalty": 1.0,
41
+ "eos_token_id": 50257,
42
+ "epsilon_cutoff": 0.0,
43
+ "eta_cutoff": 0.0,
44
+ "forced_decoder_ids": null,
45
+ "is_multilingual": true,
46
+ "lang_to_id": {
47
+ "<|af|>": 50327,
48
+ "<|am|>": 50334,
49
+ "<|ar|>": 50272,
50
+ "<|as|>": 50350,
51
+ "<|az|>": 50304,
52
+ "<|ba|>": 50355,
53
+ "<|be|>": 50330,
54
+ "<|bg|>": 50292,
55
+ "<|bn|>": 50302,
56
+ "<|bo|>": 50347,
57
+ "<|br|>": 50309,
58
+ "<|bs|>": 50315,
59
+ "<|ca|>": 50270,
60
+ "<|cs|>": 50283,
61
+ "<|cy|>": 50297,
62
+ "<|da|>": 50285,
63
+ "<|de|>": 50261,
64
+ "<|el|>": 50281,
65
+ "<|en|>": 50259,
66
+ "<|es|>": 50262,
67
+ "<|et|>": 50307,
68
+ "<|eu|>": 50310,
69
+ "<|fa|>": 50300,
70
+ "<|fi|>": 50277,
71
+ "<|fo|>": 50338,
72
+ "<|fr|>": 50265,
73
+ "<|gl|>": 50319,
74
+ "<|gu|>": 50333,
75
+ "<|haw|>": 50352,
76
+ "<|ha|>": 50354,
77
+ "<|he|>": 50279,
78
+ "<|hi|>": 50276,
79
+ "<|hr|>": 50291,
80
+ "<|ht|>": 50339,
81
+ "<|hu|>": 50286,
82
+ "<|hy|>": 50312,
83
+ "<|id|>": 50275,
84
+ "<|is|>": 50311,
85
+ "<|it|>": 50274,
86
+ "<|ja|>": 50266,
87
+ "<|jw|>": 50356,
88
+ "<|ka|>": 50329,
89
+ "<|kk|>": 50316,
90
+ "<|km|>": 50323,
91
+ "<|kn|>": 50306,
92
+ "<|ko|>": 50264,
93
+ "<|la|>": 50294,
94
+ "<|lb|>": 50345,
95
+ "<|ln|>": 50353,
96
+ "<|lo|>": 50336,
97
+ "<|lt|>": 50293,
98
+ "<|lv|>": 50301,
99
+ "<|mg|>": 50349,
100
+ "<|mi|>": 50295,
101
+ "<|mk|>": 50308,
102
+ "<|ml|>": 50296,
103
+ "<|mn|>": 50314,
104
+ "<|mr|>": 50320,
105
+ "<|ms|>": 50282,
106
+ "<|mt|>": 50343,
107
+ "<|my|>": 50346,
108
+ "<|ne|>": 50313,
109
+ "<|nl|>": 50271,
110
+ "<|nn|>": 50342,
111
+ "<|no|>": 50288,
112
+ "<|oc|>": 50328,
113
+ "<|pa|>": 50321,
114
+ "<|pl|>": 50269,
115
+ "<|ps|>": 50340,
116
+ "<|pt|>": 50267,
117
+ "<|ro|>": 50284,
118
+ "<|ru|>": 50263,
119
+ "<|sa|>": 50344,
120
+ "<|sd|>": 50332,
121
+ "<|si|>": 50322,
122
+ "<|sk|>": 50298,
123
+ "<|sl|>": 50305,
124
+ "<|sn|>": 50324,
125
+ "<|so|>": 50326,
126
+ "<|sq|>": 50317,
127
+ "<|sr|>": 50303,
128
+ "<|su|>": 50357,
129
+ "<|sv|>": 50273,
130
+ "<|sw|>": 50318,
131
+ "<|ta|>": 50287,
132
+ "<|te|>": 50299,
133
+ "<|tg|>": 50331,
134
+ "<|th|>": 50289,
135
+ "<|tk|>": 50341,
136
+ "<|tl|>": 50348,
137
+ "<|tr|>": 50268,
138
+ "<|tt|>": 50351,
139
+ "<|uk|>": 50280,
140
+ "<|ur|>": 50290,
141
+ "<|uz|>": 50337,
142
+ "<|vi|>": 50278,
143
+ "<|yi|>": 50335,
144
+ "<|yo|>": 50325,
145
+ "<|zh|>": 50260
146
+ },
147
+ "language": "hindi",
148
+ "length_penalty": 1.0,
149
+ "max_initial_timestamp_index": 50,
150
+ "max_length": 448,
151
+ "min_length": 0,
152
+ "no_repeat_ngram_size": 0,
153
+ "no_timestamps_token_id": 50363,
154
+ "num_assistant_tokens": 20,
155
+ "num_assistant_tokens_schedule": "constant",
156
+ "num_beam_groups": 1,
157
+ "num_beams": 1,
158
+ "num_return_sequences": 1,
159
+ "output_scores": false,
160
+ "pad_token_id": 50257,
161
+ "prev_sot_token_id": 50361,
162
+ "remove_invalid_values": false,
163
+ "repetition_penalty": 1.0,
164
+ "return_dict_in_generate": false,
165
+ "return_timestamps": false,
166
+ "suppress_tokens": [
167
+ 1,
168
+ 2,
169
+ 7,
170
+ 8,
171
+ 9,
172
+ 10,
173
+ 14,
174
+ 25,
175
+ 26,
176
+ 27,
177
+ 28,
178
+ 29,
179
+ 31,
180
+ 58,
181
+ 59,
182
+ 60,
183
+ 61,
184
+ 62,
185
+ 63,
186
+ 90,
187
+ 91,
188
+ 92,
189
+ 93,
190
+ 359,
191
+ 503,
192
+ 522,
193
+ 542,
194
+ 873,
195
+ 893,
196
+ 902,
197
+ 918,
198
+ 922,
199
+ 931,
200
+ 1350,
201
+ 1853,
202
+ 1982,
203
+ 2460,
204
+ 2627,
205
+ 3246,
206
+ 3253,
207
+ 3268,
208
+ 3536,
209
+ 3846,
210
+ 3961,
211
+ 4183,
212
+ 4667,
213
+ 6585,
214
+ 6647,
215
+ 7273,
216
+ 9061,
217
+ 9383,
218
+ 10428,
219
+ 10929,
220
+ 11938,
221
+ 12033,
222
+ 12331,
223
+ 12562,
224
+ 13793,
225
+ 14157,
226
+ 14635,
227
+ 15265,
228
+ 15618,
229
+ 16553,
230
+ 16604,
231
+ 18362,
232
+ 18956,
233
+ 20075,
234
+ 21675,
235
+ 22520,
236
+ 26130,
237
+ 26161,
238
+ 26435,
239
+ 28279,
240
+ 29464,
241
+ 31650,
242
+ 32302,
243
+ 32470,
244
+ 36865,
245
+ 42863,
246
+ 47425,
247
+ 49870,
248
+ 50254,
249
+ 50258,
250
+ 50358,
251
+ 50359,
252
+ 50360,
253
+ 50361,
254
+ 50362
255
+ ],
256
+ "target_lookbehind": 10,
257
+ "task": "transcribe",
258
+ "task_to_id": {
259
+ "transcribe": 50359,
260
+ "translate": 50358
261
+ },
262
+ "temperature": 1.0,
263
+ "top_k": 50,
264
+ "top_p": 1.0,
265
+ "transformers_version": "5.3.0",
266
+ "typical_p": 1.0,
267
+ "use_cache": true
268
+ }
checkpoint-2000/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bced586c32169a6cd9a39e1d8faddca7db048e3f818ad8c5fb23cb06fd17e26
3
+ size 151061672
checkpoint-2000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f686744b3642b7d2b9f0d711501b83e81b7d3e2ea21189d5a203b171051213b
3
+ size 302227787
checkpoint-2000/preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 80,
6
+ "hop_length": 160,
7
+ "n_fft": 400,
8
+ "n_samples": 480000,
9
+ "nb_max_frames": 3000,
10
+ "padding_side": "right",
11
+ "padding_value": 0.0,
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
checkpoint-2000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e97cbd8d9ee04a6b9210949dde939edfa2f2b4faccd39170a8aed9de6afab78
3
+ size 14709
checkpoint-2000/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05b8e96ba6d65181c7ad028221d70a6b870014ce444f30f4c87f1a3fe19fe20c
3
+ size 1383
checkpoint-2000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36f4b99926451a01a926e5b6c040343926d2653b170ae2a34a2bb9514da0cf5f
3
+ size 1465
checkpoint-2000/trainer_state.json ADDED
@@ -0,0 +1,630 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 1500,
3
+ "best_metric": 63.903743315508024,
4
+ "best_model_checkpoint": "./whisper-tiny-maithili/checkpoint-1500",
5
+ "epoch": 13.69982847341338,
6
+ "eval_steps": 500,
7
+ "global_step": 2000,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.17152658662092624,
14
+ "grad_norm": 18.268054962158203,
15
+ "learning_rate": 1.2000000000000002e-06,
16
+ "loss": 9.723193969726562,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.34305317324185247,
21
+ "grad_norm": 13.877284049987793,
22
+ "learning_rate": 2.4500000000000003e-06,
23
+ "loss": 8.318059692382812,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.5145797598627787,
28
+ "grad_norm": 11.479126930236816,
29
+ "learning_rate": 3.7e-06,
30
+ "loss": 6.970803833007812,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.6861063464837049,
35
+ "grad_norm": 10.104531288146973,
36
+ "learning_rate": 4.95e-06,
37
+ "loss": 5.796900634765625,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.8576329331046312,
42
+ "grad_norm": 10.247244834899902,
43
+ "learning_rate": 6.200000000000001e-06,
44
+ "loss": 4.848861389160156,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 1.0274442538593482,
49
+ "grad_norm": 7.673226356506348,
50
+ "learning_rate": 7.450000000000001e-06,
51
+ "loss": 3.985304870605469,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 1.1989708404802744,
56
+ "grad_norm": 7.689826488494873,
57
+ "learning_rate": 8.700000000000001e-06,
58
+ "loss": 3.524297180175781,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 1.3704974271012007,
63
+ "grad_norm": 8.599395751953125,
64
+ "learning_rate": 9.950000000000001e-06,
65
+ "loss": 3.220665283203125,
66
+ "step": 200
67
+ },
68
+ {
69
+ "epoch": 1.542024013722127,
70
+ "grad_norm": 8.532909393310547,
71
+ "learning_rate": 9.866666666666668e-06,
72
+ "loss": 3.0051885986328126,
73
+ "step": 225
74
+ },
75
+ {
76
+ "epoch": 1.7135506003430532,
77
+ "grad_norm": 8.584299087524414,
78
+ "learning_rate": 9.727777777777777e-06,
79
+ "loss": 2.7648504638671874,
80
+ "step": 250
81
+ },
82
+ {
83
+ "epoch": 1.8850771869639793,
84
+ "grad_norm": 8.186919212341309,
85
+ "learning_rate": 9.58888888888889e-06,
86
+ "loss": 2.6434637451171876,
87
+ "step": 275
88
+ },
89
+ {
90
+ "epoch": 2.0548885077186965,
91
+ "grad_norm": 7.06594181060791,
92
+ "learning_rate": 9.450000000000001e-06,
93
+ "loss": 2.485320739746094,
94
+ "step": 300
95
+ },
96
+ {
97
+ "epoch": 2.2264150943396226,
98
+ "grad_norm": 7.2849907875061035,
99
+ "learning_rate": 9.311111111111112e-06,
100
+ "loss": 2.2979925537109374,
101
+ "step": 325
102
+ },
103
+ {
104
+ "epoch": 2.3979416809605487,
105
+ "grad_norm": 7.386153221130371,
106
+ "learning_rate": 9.172222222222223e-06,
107
+ "loss": 2.249031982421875,
108
+ "step": 350
109
+ },
110
+ {
111
+ "epoch": 2.5694682675814753,
112
+ "grad_norm": 8.004015922546387,
113
+ "learning_rate": 9.033333333333334e-06,
114
+ "loss": 2.181380310058594,
115
+ "step": 375
116
+ },
117
+ {
118
+ "epoch": 2.7409948542024014,
119
+ "grad_norm": 6.979090213775635,
120
+ "learning_rate": 8.894444444444445e-06,
121
+ "loss": 2.1656195068359376,
122
+ "step": 400
123
+ },
124
+ {
125
+ "epoch": 2.9125214408233275,
126
+ "grad_norm": 6.589767932891846,
127
+ "learning_rate": 8.755555555555556e-06,
128
+ "loss": 2.2088014221191408,
129
+ "step": 425
130
+ },
131
+ {
132
+ "epoch": 3.0823327615780447,
133
+ "grad_norm": 8.118329048156738,
134
+ "learning_rate": 8.616666666666668e-06,
135
+ "loss": 2.0147331237792967,
136
+ "step": 450
137
+ },
138
+ {
139
+ "epoch": 3.253859348198971,
140
+ "grad_norm": 7.051534652709961,
141
+ "learning_rate": 8.477777777777778e-06,
142
+ "loss": 1.896328887939453,
143
+ "step": 475
144
+ },
145
+ {
146
+ "epoch": 3.425385934819897,
147
+ "grad_norm": 6.275884628295898,
148
+ "learning_rate": 8.33888888888889e-06,
149
+ "loss": 1.886772918701172,
150
+ "step": 500
151
+ },
152
+ {
153
+ "epoch": 3.425385934819897,
154
+ "eval_loss": 0.5728768110275269,
155
+ "eval_runtime": 92.9426,
156
+ "eval_samples_per_second": 2.797,
157
+ "eval_steps_per_second": 0.699,
158
+ "eval_wer": 68.77599524658348,
159
+ "step": 500
160
+ },
161
+ {
162
+ "epoch": 3.5969125214408235,
163
+ "grad_norm": 7.222710609436035,
164
+ "learning_rate": 8.2e-06,
165
+ "loss": 1.8691773986816407,
166
+ "step": 525
167
+ },
168
+ {
169
+ "epoch": 3.7684391080617496,
170
+ "grad_norm": 6.063198566436768,
171
+ "learning_rate": 8.061111111111112e-06,
172
+ "loss": 1.8207814025878906,
173
+ "step": 550
174
+ },
175
+ {
176
+ "epoch": 3.9399656946826758,
177
+ "grad_norm": 6.641396522521973,
178
+ "learning_rate": 7.922222222222223e-06,
179
+ "loss": 1.7857606506347656,
180
+ "step": 575
181
+ },
182
+ {
183
+ "epoch": 4.109777015437393,
184
+ "grad_norm": 6.6834397315979,
185
+ "learning_rate": 7.783333333333334e-06,
186
+ "loss": 1.713679656982422,
187
+ "step": 600
188
+ },
189
+ {
190
+ "epoch": 4.281303602058319,
191
+ "grad_norm": 6.873757362365723,
192
+ "learning_rate": 7.644444444444445e-06,
193
+ "loss": 1.6278848266601562,
194
+ "step": 625
195
+ },
196
+ {
197
+ "epoch": 4.452830188679245,
198
+ "grad_norm": 6.53254508972168,
199
+ "learning_rate": 7.505555555555556e-06,
200
+ "loss": 1.5813905334472655,
201
+ "step": 650
202
+ },
203
+ {
204
+ "epoch": 4.624356775300171,
205
+ "grad_norm": 7.650671482086182,
206
+ "learning_rate": 7.3666666666666676e-06,
207
+ "loss": 1.6567597961425782,
208
+ "step": 675
209
+ },
210
+ {
211
+ "epoch": 4.795883361921097,
212
+ "grad_norm": 6.784526348114014,
213
+ "learning_rate": 7.227777777777778e-06,
214
+ "loss": 1.6283486938476563,
215
+ "step": 700
216
+ },
217
+ {
218
+ "epoch": 4.967409948542024,
219
+ "grad_norm": 7.425609588623047,
220
+ "learning_rate": 7.0888888888888894e-06,
221
+ "loss": 1.580086669921875,
222
+ "step": 725
223
+ },
224
+ {
225
+ "epoch": 5.137221269296741,
226
+ "grad_norm": 7.560032367706299,
227
+ "learning_rate": 6.95e-06,
228
+ "loss": 1.4196165466308595,
229
+ "step": 750
230
+ },
231
+ {
232
+ "epoch": 5.308747855917667,
233
+ "grad_norm": 7.114623069763184,
234
+ "learning_rate": 6.811111111111111e-06,
235
+ "loss": 1.4393228149414063,
236
+ "step": 775
237
+ },
238
+ {
239
+ "epoch": 5.480274442538594,
240
+ "grad_norm": 6.174019813537598,
241
+ "learning_rate": 6.672222222222223e-06,
242
+ "loss": 1.4180364990234375,
243
+ "step": 800
244
+ },
245
+ {
246
+ "epoch": 5.65180102915952,
247
+ "grad_norm": 6.444286346435547,
248
+ "learning_rate": 6.533333333333334e-06,
249
+ "loss": 1.4367037963867189,
250
+ "step": 825
251
+ },
252
+ {
253
+ "epoch": 5.823327615780446,
254
+ "grad_norm": 6.457458019256592,
255
+ "learning_rate": 6.394444444444445e-06,
256
+ "loss": 1.4541001892089844,
257
+ "step": 850
258
+ },
259
+ {
260
+ "epoch": 5.994854202401372,
261
+ "grad_norm": 6.65748929977417,
262
+ "learning_rate": 6.255555555555556e-06,
263
+ "loss": 1.4775286865234376,
264
+ "step": 875
265
+ },
266
+ {
267
+ "epoch": 6.164665523156089,
268
+ "grad_norm": 6.2816057205200195,
269
+ "learning_rate": 6.116666666666668e-06,
270
+ "loss": 1.2730085754394531,
271
+ "step": 900
272
+ },
273
+ {
274
+ "epoch": 6.3361921097770155,
275
+ "grad_norm": 6.40878963470459,
276
+ "learning_rate": 5.977777777777778e-06,
277
+ "loss": 1.2837075805664062,
278
+ "step": 925
279
+ },
280
+ {
281
+ "epoch": 6.507718696397942,
282
+ "grad_norm": 6.427629470825195,
283
+ "learning_rate": 5.8388888888888895e-06,
284
+ "loss": 1.2479456329345704,
285
+ "step": 950
286
+ },
287
+ {
288
+ "epoch": 6.679245283018868,
289
+ "grad_norm": 5.938961982727051,
290
+ "learning_rate": 5.7e-06,
291
+ "loss": 1.3641961669921876,
292
+ "step": 975
293
+ },
294
+ {
295
+ "epoch": 6.850771869639794,
296
+ "grad_norm": 6.981799125671387,
297
+ "learning_rate": 5.561111111111111e-06,
298
+ "loss": 1.2829299926757813,
299
+ "step": 1000
300
+ },
301
+ {
302
+ "epoch": 6.850771869639794,
303
+ "eval_loss": 0.5365099906921387,
304
+ "eval_runtime": 92.6416,
305
+ "eval_samples_per_second": 2.807,
306
+ "eval_steps_per_second": 0.702,
307
+ "eval_wer": 64.67617349970291,
308
+ "step": 1000
309
+ },
310
+ {
311
+ "epoch": 7.020583190394511,
312
+ "grad_norm": 6.462595462799072,
313
+ "learning_rate": 5.422222222222223e-06,
314
+ "loss": 1.266632080078125,
315
+ "step": 1025
316
+ },
317
+ {
318
+ "epoch": 7.192109777015437,
319
+ "grad_norm": 6.442847728729248,
320
+ "learning_rate": 5.283333333333333e-06,
321
+ "loss": 1.1616410827636718,
322
+ "step": 1050
323
+ },
324
+ {
325
+ "epoch": 7.363636363636363,
326
+ "grad_norm": 5.910035133361816,
327
+ "learning_rate": 5.144444444444445e-06,
328
+ "loss": 1.1423403167724608,
329
+ "step": 1075
330
+ },
331
+ {
332
+ "epoch": 7.535162950257289,
333
+ "grad_norm": 6.2111334800720215,
334
+ "learning_rate": 5.005555555555556e-06,
335
+ "loss": 1.1994317626953126,
336
+ "step": 1100
337
+ },
338
+ {
339
+ "epoch": 7.7066895368782165,
340
+ "grad_norm": 5.6760783195495605,
341
+ "learning_rate": 4.866666666666667e-06,
342
+ "loss": 1.1873680877685546,
343
+ "step": 1125
344
+ },
345
+ {
346
+ "epoch": 7.878216123499143,
347
+ "grad_norm": 6.996194839477539,
348
+ "learning_rate": 4.727777777777779e-06,
349
+ "loss": 1.1682706451416016,
350
+ "step": 1150
351
+ },
352
+ {
353
+ "epoch": 8.04802744425386,
354
+ "grad_norm": 5.388121604919434,
355
+ "learning_rate": 4.58888888888889e-06,
356
+ "loss": 1.1501982879638672,
357
+ "step": 1175
358
+ },
359
+ {
360
+ "epoch": 8.219554030874786,
361
+ "grad_norm": 6.324208736419678,
362
+ "learning_rate": 4.450000000000001e-06,
363
+ "loss": 1.0414784240722657,
364
+ "step": 1200
365
+ },
366
+ {
367
+ "epoch": 8.391080617495712,
368
+ "grad_norm": 6.224495887756348,
369
+ "learning_rate": 4.3111111111111115e-06,
370
+ "loss": 1.0576978302001954,
371
+ "step": 1225
372
+ },
373
+ {
374
+ "epoch": 8.562607204116638,
375
+ "grad_norm": 5.9399094581604,
376
+ "learning_rate": 4.1722222222222225e-06,
377
+ "loss": 1.0483750915527343,
378
+ "step": 1250
379
+ },
380
+ {
381
+ "epoch": 8.734133790737564,
382
+ "grad_norm": 6.331912994384766,
383
+ "learning_rate": 4.033333333333333e-06,
384
+ "loss": 1.0921112060546876,
385
+ "step": 1275
386
+ },
387
+ {
388
+ "epoch": 8.90566037735849,
389
+ "grad_norm": 7.319565296173096,
390
+ "learning_rate": 3.894444444444444e-06,
391
+ "loss": 1.0816537475585937,
392
+ "step": 1300
393
+ },
394
+ {
395
+ "epoch": 9.075471698113208,
396
+ "grad_norm": 6.406201362609863,
397
+ "learning_rate": 3.7555555555555557e-06,
398
+ "loss": 1.0307456207275392,
399
+ "step": 1325
400
+ },
401
+ {
402
+ "epoch": 9.246998284734135,
403
+ "grad_norm": 6.348610877990723,
404
+ "learning_rate": 3.616666666666667e-06,
405
+ "loss": 0.9632396697998047,
406
+ "step": 1350
407
+ },
408
+ {
409
+ "epoch": 9.41852487135506,
410
+ "grad_norm": 6.033849239349365,
411
+ "learning_rate": 3.4777777777777784e-06,
412
+ "loss": 0.9932768249511719,
413
+ "step": 1375
414
+ },
415
+ {
416
+ "epoch": 9.590051457975987,
417
+ "grad_norm": 6.423510551452637,
418
+ "learning_rate": 3.3388888888888893e-06,
419
+ "loss": 0.978936538696289,
420
+ "step": 1400
421
+ },
422
+ {
423
+ "epoch": 9.761578044596913,
424
+ "grad_norm": 5.581418514251709,
425
+ "learning_rate": 3.2000000000000003e-06,
426
+ "loss": 0.9529872894287109,
427
+ "step": 1425
428
+ },
429
+ {
430
+ "epoch": 9.933104631217839,
431
+ "grad_norm": 7.128633499145508,
432
+ "learning_rate": 3.0611111111111112e-06,
433
+ "loss": 1.00614990234375,
434
+ "step": 1450
435
+ },
436
+ {
437
+ "epoch": 10.102915951972555,
438
+ "grad_norm": 6.873051643371582,
439
+ "learning_rate": 2.9222222222222226e-06,
440
+ "loss": 0.9351605224609375,
441
+ "step": 1475
442
+ },
443
+ {
444
+ "epoch": 10.274442538593481,
445
+ "grad_norm": 6.594143390655518,
446
+ "learning_rate": 2.7833333333333335e-06,
447
+ "loss": 0.8834098815917969,
448
+ "step": 1500
449
+ },
450
+ {
451
+ "epoch": 10.274442538593481,
452
+ "eval_loss": 0.5569483637809753,
453
+ "eval_runtime": 93.3641,
454
+ "eval_samples_per_second": 2.785,
455
+ "eval_steps_per_second": 0.696,
456
+ "eval_wer": 63.903743315508024,
457
+ "step": 1500
458
+ },
459
+ {
460
+ "epoch": 10.445969125214408,
461
+ "grad_norm": 6.543798446655273,
462
+ "learning_rate": 2.6444444444444444e-06,
463
+ "loss": 0.9357952880859375,
464
+ "step": 1525
465
+ },
466
+ {
467
+ "epoch": 10.617495711835334,
468
+ "grad_norm": 5.903841018676758,
469
+ "learning_rate": 2.5055555555555554e-06,
470
+ "loss": 0.8977721405029296,
471
+ "step": 1550
472
+ },
473
+ {
474
+ "epoch": 10.78902229845626,
475
+ "grad_norm": 5.874545574188232,
476
+ "learning_rate": 2.3666666666666667e-06,
477
+ "loss": 0.8883360290527343,
478
+ "step": 1575
479
+ },
480
+ {
481
+ "epoch": 10.960548885077188,
482
+ "grad_norm": 6.661474227905273,
483
+ "learning_rate": 2.2277777777777777e-06,
484
+ "loss": 0.920865249633789,
485
+ "step": 1600
486
+ },
487
+ {
488
+ "epoch": 11.130360205831904,
489
+ "grad_norm": 5.809503555297852,
490
+ "learning_rate": 2.088888888888889e-06,
491
+ "loss": 0.8493796539306641,
492
+ "step": 1625
493
+ },
494
+ {
495
+ "epoch": 11.30188679245283,
496
+ "grad_norm": 5.753544807434082,
497
+ "learning_rate": 1.9500000000000004e-06,
498
+ "loss": 0.825905532836914,
499
+ "step": 1650
500
+ },
501
+ {
502
+ "epoch": 11.473413379073756,
503
+ "grad_norm": 6.0916972160339355,
504
+ "learning_rate": 1.8111111111111113e-06,
505
+ "loss": 0.8476572418212891,
506
+ "step": 1675
507
+ },
508
+ {
509
+ "epoch": 11.644939965694682,
510
+ "grad_norm": 6.63301420211792,
511
+ "learning_rate": 1.6722222222222223e-06,
512
+ "loss": 0.8341015625,
513
+ "step": 1700
514
+ },
515
+ {
516
+ "epoch": 11.816466552315608,
517
+ "grad_norm": 5.515976428985596,
518
+ "learning_rate": 1.5333333333333334e-06,
519
+ "loss": 0.8632970428466797,
520
+ "step": 1725
521
+ },
522
+ {
523
+ "epoch": 11.987993138936535,
524
+ "grad_norm": 5.419062614440918,
525
+ "learning_rate": 1.3944444444444446e-06,
526
+ "loss": 0.8705248260498046,
527
+ "step": 1750
528
+ },
529
+ {
530
+ "epoch": 12.157804459691253,
531
+ "grad_norm": 5.655745506286621,
532
+ "learning_rate": 1.2555555555555557e-06,
533
+ "loss": 0.7931866455078125,
534
+ "step": 1775
535
+ },
536
+ {
537
+ "epoch": 12.329331046312179,
538
+ "grad_norm": 5.437541961669922,
539
+ "learning_rate": 1.1166666666666666e-06,
540
+ "loss": 0.813487548828125,
541
+ "step": 1800
542
+ },
543
+ {
544
+ "epoch": 12.500857632933105,
545
+ "grad_norm": 5.816484451293945,
546
+ "learning_rate": 9.77777777777778e-07,
547
+ "loss": 0.8068718719482422,
548
+ "step": 1825
549
+ },
550
+ {
551
+ "epoch": 12.672384219554031,
552
+ "grad_norm": 5.428255081176758,
553
+ "learning_rate": 8.388888888888889e-07,
554
+ "loss": 0.7925386810302735,
555
+ "step": 1850
556
+ },
557
+ {
558
+ "epoch": 12.843910806174957,
559
+ "grad_norm": 5.579376220703125,
560
+ "learning_rate": 7.000000000000001e-07,
561
+ "loss": 0.8237639617919922,
562
+ "step": 1875
563
+ },
564
+ {
565
+ "epoch": 13.013722126929673,
566
+ "grad_norm": 5.45307731628418,
567
+ "learning_rate": 5.611111111111111e-07,
568
+ "loss": 0.7975894165039062,
569
+ "step": 1900
570
+ },
571
+ {
572
+ "epoch": 13.1852487135506,
573
+ "grad_norm": 5.217875003814697,
574
+ "learning_rate": 4.2222222222222226e-07,
575
+ "loss": 0.8227002716064453,
576
+ "step": 1925
577
+ },
578
+ {
579
+ "epoch": 13.356775300171527,
580
+ "grad_norm": 5.0090155601501465,
581
+ "learning_rate": 2.8333333333333336e-07,
582
+ "loss": 0.7616297149658203,
583
+ "step": 1950
584
+ },
585
+ {
586
+ "epoch": 13.528301886792454,
587
+ "grad_norm": 5.426841735839844,
588
+ "learning_rate": 1.4444444444444445e-07,
589
+ "loss": 0.7497710418701172,
590
+ "step": 1975
591
+ },
592
+ {
593
+ "epoch": 13.69982847341338,
594
+ "grad_norm": 5.744300365447998,
595
+ "learning_rate": 5.555555555555556e-09,
596
+ "loss": 0.8125200653076172,
597
+ "step": 2000
598
+ },
599
+ {
600
+ "epoch": 13.69982847341338,
601
+ "eval_loss": 0.5726562738418579,
602
+ "eval_runtime": 93.1097,
603
+ "eval_samples_per_second": 2.792,
604
+ "eval_steps_per_second": 0.698,
605
+ "eval_wer": 64.20083184789067,
606
+ "step": 2000
607
+ }
608
+ ],
609
+ "logging_steps": 25,
610
+ "max_steps": 2000,
611
+ "num_input_tokens_seen": 0,
612
+ "num_train_epochs": 14,
613
+ "save_steps": 500,
614
+ "stateful_callbacks": {
615
+ "TrainerControl": {
616
+ "args": {
617
+ "should_epoch_stop": false,
618
+ "should_evaluate": false,
619
+ "should_log": false,
620
+ "should_save": true,
621
+ "should_training_stop": true
622
+ },
623
+ "attributes": {}
624
+ }
625
+ },
626
+ "total_flos": 7.8652414181376e+17,
627
+ "train_batch_size": 4,
628
+ "trial_name": null,
629
+ "trial_params": null
630
+ }
checkpoint-2000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d3768d5597d6e5a7d63118e80f44059101c56bf60f8f4722ac7e1bcfe7d31f
3
+ size 5329
checkpoint-500/config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 50257,
10
+ "classifier_proj_size": 256,
11
+ "d_model": 384,
12
+ "decoder_attention_heads": 6,
13
+ "decoder_ffn_dim": 1536,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 4,
16
+ "decoder_start_token_id": 50258,
17
+ "dropout": 0.0,
18
+ "dtype": "float32",
19
+ "encoder_attention_heads": 6,
20
+ "encoder_ffn_dim": 1536,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 4,
23
+ "eos_token_id": 50257,
24
+ "forced_decoder_ids": [
25
+ [
26
+ 1,
27
+ 50259
28
+ ],
29
+ [
30
+ 2,
31
+ 50359
32
+ ],
33
+ [
34
+ 3,
35
+ 50363
36
+ ]
37
+ ],
38
+ "init_std": 0.02,
39
+ "is_encoder_decoder": true,
40
+ "mask_feature_length": 10,
41
+ "mask_feature_min_masks": 0,
42
+ "mask_feature_prob": 0.0,
43
+ "mask_time_length": 10,
44
+ "mask_time_min_masks": 2,
45
+ "mask_time_prob": 0.05,
46
+ "max_source_positions": 1500,
47
+ "max_target_positions": 448,
48
+ "median_filter_width": 7,
49
+ "model_type": "whisper",
50
+ "num_hidden_layers": 4,
51
+ "num_mel_bins": 80,
52
+ "pad_token_id": 50257,
53
+ "scale_embedding": false,
54
+ "tie_word_embeddings": true,
55
+ "transformers_version": "5.3.0",
56
+ "use_cache": false,
57
+ "use_weighted_layer_sum": false,
58
+ "vocab_size": 51865
59
+ }
checkpoint-500/generation_config.json ADDED
@@ -0,0 +1,268 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 2
6
+ ],
7
+ [
8
+ 3,
9
+ 0
10
+ ],
11
+ [
12
+ 3,
13
+ 2
14
+ ],
15
+ [
16
+ 3,
17
+ 3
18
+ ],
19
+ [
20
+ 3,
21
+ 4
22
+ ],
23
+ [
24
+ 3,
25
+ 5
26
+ ]
27
+ ],
28
+ "assistant_confidence_threshold": 0.4,
29
+ "assistant_lookbehind": 10,
30
+ "begin_suppress_tokens": [
31
+ 220,
32
+ 50257
33
+ ],
34
+ "bos_token_id": 50257,
35
+ "decoder_start_token_id": 50258,
36
+ "diversity_penalty": 0.0,
37
+ "do_sample": false,
38
+ "early_stopping": false,
39
+ "encoder_no_repeat_ngram_size": 0,
40
+ "encoder_repetition_penalty": 1.0,
41
+ "eos_token_id": 50257,
42
+ "epsilon_cutoff": 0.0,
43
+ "eta_cutoff": 0.0,
44
+ "forced_decoder_ids": null,
45
+ "is_multilingual": true,
46
+ "lang_to_id": {
47
+ "<|af|>": 50327,
48
+ "<|am|>": 50334,
49
+ "<|ar|>": 50272,
50
+ "<|as|>": 50350,
51
+ "<|az|>": 50304,
52
+ "<|ba|>": 50355,
53
+ "<|be|>": 50330,
54
+ "<|bg|>": 50292,
55
+ "<|bn|>": 50302,
56
+ "<|bo|>": 50347,
57
+ "<|br|>": 50309,
58
+ "<|bs|>": 50315,
59
+ "<|ca|>": 50270,
60
+ "<|cs|>": 50283,
61
+ "<|cy|>": 50297,
62
+ "<|da|>": 50285,
63
+ "<|de|>": 50261,
64
+ "<|el|>": 50281,
65
+ "<|en|>": 50259,
66
+ "<|es|>": 50262,
67
+ "<|et|>": 50307,
68
+ "<|eu|>": 50310,
69
+ "<|fa|>": 50300,
70
+ "<|fi|>": 50277,
71
+ "<|fo|>": 50338,
72
+ "<|fr|>": 50265,
73
+ "<|gl|>": 50319,
74
+ "<|gu|>": 50333,
75
+ "<|haw|>": 50352,
76
+ "<|ha|>": 50354,
77
+ "<|he|>": 50279,
78
+ "<|hi|>": 50276,
79
+ "<|hr|>": 50291,
80
+ "<|ht|>": 50339,
81
+ "<|hu|>": 50286,
82
+ "<|hy|>": 50312,
83
+ "<|id|>": 50275,
84
+ "<|is|>": 50311,
85
+ "<|it|>": 50274,
86
+ "<|ja|>": 50266,
87
+ "<|jw|>": 50356,
88
+ "<|ka|>": 50329,
89
+ "<|kk|>": 50316,
90
+ "<|km|>": 50323,
91
+ "<|kn|>": 50306,
92
+ "<|ko|>": 50264,
93
+ "<|la|>": 50294,
94
+ "<|lb|>": 50345,
95
+ "<|ln|>": 50353,
96
+ "<|lo|>": 50336,
97
+ "<|lt|>": 50293,
98
+ "<|lv|>": 50301,
99
+ "<|mg|>": 50349,
100
+ "<|mi|>": 50295,
101
+ "<|mk|>": 50308,
102
+ "<|ml|>": 50296,
103
+ "<|mn|>": 50314,
104
+ "<|mr|>": 50320,
105
+ "<|ms|>": 50282,
106
+ "<|mt|>": 50343,
107
+ "<|my|>": 50346,
108
+ "<|ne|>": 50313,
109
+ "<|nl|>": 50271,
110
+ "<|nn|>": 50342,
111
+ "<|no|>": 50288,
112
+ "<|oc|>": 50328,
113
+ "<|pa|>": 50321,
114
+ "<|pl|>": 50269,
115
+ "<|ps|>": 50340,
116
+ "<|pt|>": 50267,
117
+ "<|ro|>": 50284,
118
+ "<|ru|>": 50263,
119
+ "<|sa|>": 50344,
120
+ "<|sd|>": 50332,
121
+ "<|si|>": 50322,
122
+ "<|sk|>": 50298,
123
+ "<|sl|>": 50305,
124
+ "<|sn|>": 50324,
125
+ "<|so|>": 50326,
126
+ "<|sq|>": 50317,
127
+ "<|sr|>": 50303,
128
+ "<|su|>": 50357,
129
+ "<|sv|>": 50273,
130
+ "<|sw|>": 50318,
131
+ "<|ta|>": 50287,
132
+ "<|te|>": 50299,
133
+ "<|tg|>": 50331,
134
+ "<|th|>": 50289,
135
+ "<|tk|>": 50341,
136
+ "<|tl|>": 50348,
137
+ "<|tr|>": 50268,
138
+ "<|tt|>": 50351,
139
+ "<|uk|>": 50280,
140
+ "<|ur|>": 50290,
141
+ "<|uz|>": 50337,
142
+ "<|vi|>": 50278,
143
+ "<|yi|>": 50335,
144
+ "<|yo|>": 50325,
145
+ "<|zh|>": 50260
146
+ },
147
+ "language": "hindi",
148
+ "length_penalty": 1.0,
149
+ "max_initial_timestamp_index": 50,
150
+ "max_length": 448,
151
+ "min_length": 0,
152
+ "no_repeat_ngram_size": 0,
153
+ "no_timestamps_token_id": 50363,
154
+ "num_assistant_tokens": 20,
155
+ "num_assistant_tokens_schedule": "constant",
156
+ "num_beam_groups": 1,
157
+ "num_beams": 1,
158
+ "num_return_sequences": 1,
159
+ "output_scores": false,
160
+ "pad_token_id": 50257,
161
+ "prev_sot_token_id": 50361,
162
+ "remove_invalid_values": false,
163
+ "repetition_penalty": 1.0,
164
+ "return_dict_in_generate": false,
165
+ "return_timestamps": false,
166
+ "suppress_tokens": [
167
+ 1,
168
+ 2,
169
+ 7,
170
+ 8,
171
+ 9,
172
+ 10,
173
+ 14,
174
+ 25,
175
+ 26,
176
+ 27,
177
+ 28,
178
+ 29,
179
+ 31,
180
+ 58,
181
+ 59,
182
+ 60,
183
+ 61,
184
+ 62,
185
+ 63,
186
+ 90,
187
+ 91,
188
+ 92,
189
+ 93,
190
+ 359,
191
+ 503,
192
+ 522,
193
+ 542,
194
+ 873,
195
+ 893,
196
+ 902,
197
+ 918,
198
+ 922,
199
+ 931,
200
+ 1350,
201
+ 1853,
202
+ 1982,
203
+ 2460,
204
+ 2627,
205
+ 3246,
206
+ 3253,
207
+ 3268,
208
+ 3536,
209
+ 3846,
210
+ 3961,
211
+ 4183,
212
+ 4667,
213
+ 6585,
214
+ 6647,
215
+ 7273,
216
+ 9061,
217
+ 9383,
218
+ 10428,
219
+ 10929,
220
+ 11938,
221
+ 12033,
222
+ 12331,
223
+ 12562,
224
+ 13793,
225
+ 14157,
226
+ 14635,
227
+ 15265,
228
+ 15618,
229
+ 16553,
230
+ 16604,
231
+ 18362,
232
+ 18956,
233
+ 20075,
234
+ 21675,
235
+ 22520,
236
+ 26130,
237
+ 26161,
238
+ 26435,
239
+ 28279,
240
+ 29464,
241
+ 31650,
242
+ 32302,
243
+ 32470,
244
+ 36865,
245
+ 42863,
246
+ 47425,
247
+ 49870,
248
+ 50254,
249
+ 50258,
250
+ 50358,
251
+ 50359,
252
+ 50360,
253
+ 50361,
254
+ 50362
255
+ ],
256
+ "target_lookbehind": 10,
257
+ "task": "transcribe",
258
+ "task_to_id": {
259
+ "transcribe": 50359,
260
+ "translate": 50358
261
+ },
262
+ "temperature": 1.0,
263
+ "top_k": 50,
264
+ "top_p": 1.0,
265
+ "transformers_version": "5.3.0",
266
+ "typical_p": 1.0,
267
+ "use_cache": true
268
+ }
checkpoint-500/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f994478a3a7c93c80fa8408b08a5bbd2d0e28c4966ecb32c740a84bc361cb8d
3
+ size 151061672
checkpoint-500/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:258a8a7f74f29607c097da5e0cc933d7c9ca87258447a870fd4a05d5cc376ee7
3
+ size 302227787
checkpoint-500/preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 80,
6
+ "hop_length": 160,
7
+ "n_fft": 400,
8
+ "n_samples": 480000,
9
+ "nb_max_frames": 3000,
10
+ "padding_side": "right",
11
+ "padding_value": 0.0,
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
checkpoint-500/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0f4530c71a2aaafca67ad190b16712615eb122172a8f17402ae2756ffbd4156
3
+ size 14709
checkpoint-500/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:447e41e8c7b04858ad91628e58d3582d0aaeae5da4bd759d93c7bd15084ffdbf
3
+ size 1383
checkpoint-500/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8fc650f91efe99e73064c3ce2e8f28a11637fb01902c1ecfb1c00d9de12d65c
3
+ size 1465
checkpoint-500/trainer_state.json ADDED
@@ -0,0 +1,183 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 500,
3
+ "best_metric": 68.77599524658348,
4
+ "best_model_checkpoint": "./whisper-tiny-maithili/checkpoint-500",
5
+ "epoch": 3.425385934819897,
6
+ "eval_steps": 500,
7
+ "global_step": 500,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.17152658662092624,
14
+ "grad_norm": 18.268054962158203,
15
+ "learning_rate": 1.2000000000000002e-06,
16
+ "loss": 9.723193969726562,
17
+ "step": 25
18
+ },
19
+ {
20
+ "epoch": 0.34305317324185247,
21
+ "grad_norm": 13.877284049987793,
22
+ "learning_rate": 2.4500000000000003e-06,
23
+ "loss": 8.318059692382812,
24
+ "step": 50
25
+ },
26
+ {
27
+ "epoch": 0.5145797598627787,
28
+ "grad_norm": 11.479126930236816,
29
+ "learning_rate": 3.7e-06,
30
+ "loss": 6.970803833007812,
31
+ "step": 75
32
+ },
33
+ {
34
+ "epoch": 0.6861063464837049,
35
+ "grad_norm": 10.104531288146973,
36
+ "learning_rate": 4.95e-06,
37
+ "loss": 5.796900634765625,
38
+ "step": 100
39
+ },
40
+ {
41
+ "epoch": 0.8576329331046312,
42
+ "grad_norm": 10.247244834899902,
43
+ "learning_rate": 6.200000000000001e-06,
44
+ "loss": 4.848861389160156,
45
+ "step": 125
46
+ },
47
+ {
48
+ "epoch": 1.0274442538593482,
49
+ "grad_norm": 7.673226356506348,
50
+ "learning_rate": 7.450000000000001e-06,
51
+ "loss": 3.985304870605469,
52
+ "step": 150
53
+ },
54
+ {
55
+ "epoch": 1.1989708404802744,
56
+ "grad_norm": 7.689826488494873,
57
+ "learning_rate": 8.700000000000001e-06,
58
+ "loss": 3.524297180175781,
59
+ "step": 175
60
+ },
61
+ {
62
+ "epoch": 1.3704974271012007,
63
+ "grad_norm": 8.599395751953125,
64
+ "learning_rate": 9.950000000000001e-06,
65
+ "loss": 3.220665283203125,
66
+ "step": 200
67
+ },
68
+ {
69
+ "epoch": 1.542024013722127,
70
+ "grad_norm": 8.532909393310547,
71
+ "learning_rate": 9.866666666666668e-06,
72
+ "loss": 3.0051885986328126,
73
+ "step": 225
74
+ },
75
+ {
76
+ "epoch": 1.7135506003430532,
77
+ "grad_norm": 8.584299087524414,
78
+ "learning_rate": 9.727777777777777e-06,
79
+ "loss": 2.7648504638671874,
80
+ "step": 250
81
+ },
82
+ {
83
+ "epoch": 1.8850771869639793,
84
+ "grad_norm": 8.186919212341309,
85
+ "learning_rate": 9.58888888888889e-06,
86
+ "loss": 2.6434637451171876,
87
+ "step": 275
88
+ },
89
+ {
90
+ "epoch": 2.0548885077186965,
91
+ "grad_norm": 7.06594181060791,
92
+ "learning_rate": 9.450000000000001e-06,
93
+ "loss": 2.485320739746094,
94
+ "step": 300
95
+ },
96
+ {
97
+ "epoch": 2.2264150943396226,
98
+ "grad_norm": 7.2849907875061035,
99
+ "learning_rate": 9.311111111111112e-06,
100
+ "loss": 2.2979925537109374,
101
+ "step": 325
102
+ },
103
+ {
104
+ "epoch": 2.3979416809605487,
105
+ "grad_norm": 7.386153221130371,
106
+ "learning_rate": 9.172222222222223e-06,
107
+ "loss": 2.249031982421875,
108
+ "step": 350
109
+ },
110
+ {
111
+ "epoch": 2.5694682675814753,
112
+ "grad_norm": 8.004015922546387,
113
+ "learning_rate": 9.033333333333334e-06,
114
+ "loss": 2.181380310058594,
115
+ "step": 375
116
+ },
117
+ {
118
+ "epoch": 2.7409948542024014,
119
+ "grad_norm": 6.979090213775635,
120
+ "learning_rate": 8.894444444444445e-06,
121
+ "loss": 2.1656195068359376,
122
+ "step": 400
123
+ },
124
+ {
125
+ "epoch": 2.9125214408233275,
126
+ "grad_norm": 6.589767932891846,
127
+ "learning_rate": 8.755555555555556e-06,
128
+ "loss": 2.2088014221191408,
129
+ "step": 425
130
+ },
131
+ {
132
+ "epoch": 3.0823327615780447,
133
+ "grad_norm": 8.118329048156738,
134
+ "learning_rate": 8.616666666666668e-06,
135
+ "loss": 2.0147331237792967,
136
+ "step": 450
137
+ },
138
+ {
139
+ "epoch": 3.253859348198971,
140
+ "grad_norm": 7.051534652709961,
141
+ "learning_rate": 8.477777777777778e-06,
142
+ "loss": 1.896328887939453,
143
+ "step": 475
144
+ },
145
+ {
146
+ "epoch": 3.425385934819897,
147
+ "grad_norm": 6.275884628295898,
148
+ "learning_rate": 8.33888888888889e-06,
149
+ "loss": 1.886772918701172,
150
+ "step": 500
151
+ },
152
+ {
153
+ "epoch": 3.425385934819897,
154
+ "eval_loss": 0.5728768110275269,
155
+ "eval_runtime": 92.9426,
156
+ "eval_samples_per_second": 2.797,
157
+ "eval_steps_per_second": 0.699,
158
+ "eval_wer": 68.77599524658348,
159
+ "step": 500
160
+ }
161
+ ],
162
+ "logging_steps": 25,
163
+ "max_steps": 2000,
164
+ "num_input_tokens_seen": 0,
165
+ "num_train_epochs": 14,
166
+ "save_steps": 500,
167
+ "stateful_callbacks": {
168
+ "TrainerControl": {
169
+ "args": {
170
+ "should_epoch_stop": false,
171
+ "should_evaluate": false,
172
+ "should_log": false,
173
+ "should_save": true,
174
+ "should_training_stop": false
175
+ },
176
+ "attributes": {}
177
+ }
178
+ },
179
+ "total_flos": 1.9665565433856e+17,
180
+ "train_batch_size": 4,
181
+ "trial_name": null,
182
+ "trial_params": null
183
+ }
checkpoint-500/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d3768d5597d6e5a7d63118e80f44059101c56bf60f8f4722ac7e1bcfe7d31f
3
+ size 5329
config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "activation_function": "gelu",
4
+ "apply_spec_augment": false,
5
+ "architectures": [
6
+ "WhisperForConditionalGeneration"
7
+ ],
8
+ "attention_dropout": 0.0,
9
+ "bos_token_id": 50257,
10
+ "classifier_proj_size": 256,
11
+ "d_model": 384,
12
+ "decoder_attention_heads": 6,
13
+ "decoder_ffn_dim": 1536,
14
+ "decoder_layerdrop": 0.0,
15
+ "decoder_layers": 4,
16
+ "decoder_start_token_id": 50258,
17
+ "dropout": 0.0,
18
+ "dtype": "float32",
19
+ "encoder_attention_heads": 6,
20
+ "encoder_ffn_dim": 1536,
21
+ "encoder_layerdrop": 0.0,
22
+ "encoder_layers": 4,
23
+ "eos_token_id": 50257,
24
+ "forced_decoder_ids": [
25
+ [
26
+ 1,
27
+ 50259
28
+ ],
29
+ [
30
+ 2,
31
+ 50359
32
+ ],
33
+ [
34
+ 3,
35
+ 50363
36
+ ]
37
+ ],
38
+ "init_std": 0.02,
39
+ "is_encoder_decoder": true,
40
+ "mask_feature_length": 10,
41
+ "mask_feature_min_masks": 0,
42
+ "mask_feature_prob": 0.0,
43
+ "mask_time_length": 10,
44
+ "mask_time_min_masks": 2,
45
+ "mask_time_prob": 0.05,
46
+ "max_source_positions": 1500,
47
+ "max_target_positions": 448,
48
+ "median_filter_width": 7,
49
+ "model_type": "whisper",
50
+ "num_hidden_layers": 4,
51
+ "num_mel_bins": 80,
52
+ "pad_token_id": 50257,
53
+ "scale_embedding": false,
54
+ "tie_word_embeddings": true,
55
+ "transformers_version": "5.3.0",
56
+ "use_cache": false,
57
+ "use_weighted_layer_sum": false,
58
+ "vocab_size": 51865
59
+ }
generation_config.json ADDED
@@ -0,0 +1,268 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "alignment_heads": [
3
+ [
4
+ 2,
5
+ 2
6
+ ],
7
+ [
8
+ 3,
9
+ 0
10
+ ],
11
+ [
12
+ 3,
13
+ 2
14
+ ],
15
+ [
16
+ 3,
17
+ 3
18
+ ],
19
+ [
20
+ 3,
21
+ 4
22
+ ],
23
+ [
24
+ 3,
25
+ 5
26
+ ]
27
+ ],
28
+ "assistant_confidence_threshold": 0.4,
29
+ "assistant_lookbehind": 10,
30
+ "begin_suppress_tokens": [
31
+ 220,
32
+ 50257
33
+ ],
34
+ "bos_token_id": 50257,
35
+ "decoder_start_token_id": 50258,
36
+ "diversity_penalty": 0.0,
37
+ "do_sample": false,
38
+ "early_stopping": false,
39
+ "encoder_no_repeat_ngram_size": 0,
40
+ "encoder_repetition_penalty": 1.0,
41
+ "eos_token_id": 50257,
42
+ "epsilon_cutoff": 0.0,
43
+ "eta_cutoff": 0.0,
44
+ "forced_decoder_ids": null,
45
+ "is_multilingual": true,
46
+ "lang_to_id": {
47
+ "<|af|>": 50327,
48
+ "<|am|>": 50334,
49
+ "<|ar|>": 50272,
50
+ "<|as|>": 50350,
51
+ "<|az|>": 50304,
52
+ "<|ba|>": 50355,
53
+ "<|be|>": 50330,
54
+ "<|bg|>": 50292,
55
+ "<|bn|>": 50302,
56
+ "<|bo|>": 50347,
57
+ "<|br|>": 50309,
58
+ "<|bs|>": 50315,
59
+ "<|ca|>": 50270,
60
+ "<|cs|>": 50283,
61
+ "<|cy|>": 50297,
62
+ "<|da|>": 50285,
63
+ "<|de|>": 50261,
64
+ "<|el|>": 50281,
65
+ "<|en|>": 50259,
66
+ "<|es|>": 50262,
67
+ "<|et|>": 50307,
68
+ "<|eu|>": 50310,
69
+ "<|fa|>": 50300,
70
+ "<|fi|>": 50277,
71
+ "<|fo|>": 50338,
72
+ "<|fr|>": 50265,
73
+ "<|gl|>": 50319,
74
+ "<|gu|>": 50333,
75
+ "<|haw|>": 50352,
76
+ "<|ha|>": 50354,
77
+ "<|he|>": 50279,
78
+ "<|hi|>": 50276,
79
+ "<|hr|>": 50291,
80
+ "<|ht|>": 50339,
81
+ "<|hu|>": 50286,
82
+ "<|hy|>": 50312,
83
+ "<|id|>": 50275,
84
+ "<|is|>": 50311,
85
+ "<|it|>": 50274,
86
+ "<|ja|>": 50266,
87
+ "<|jw|>": 50356,
88
+ "<|ka|>": 50329,
89
+ "<|kk|>": 50316,
90
+ "<|km|>": 50323,
91
+ "<|kn|>": 50306,
92
+ "<|ko|>": 50264,
93
+ "<|la|>": 50294,
94
+ "<|lb|>": 50345,
95
+ "<|ln|>": 50353,
96
+ "<|lo|>": 50336,
97
+ "<|lt|>": 50293,
98
+ "<|lv|>": 50301,
99
+ "<|mg|>": 50349,
100
+ "<|mi|>": 50295,
101
+ "<|mk|>": 50308,
102
+ "<|ml|>": 50296,
103
+ "<|mn|>": 50314,
104
+ "<|mr|>": 50320,
105
+ "<|ms|>": 50282,
106
+ "<|mt|>": 50343,
107
+ "<|my|>": 50346,
108
+ "<|ne|>": 50313,
109
+ "<|nl|>": 50271,
110
+ "<|nn|>": 50342,
111
+ "<|no|>": 50288,
112
+ "<|oc|>": 50328,
113
+ "<|pa|>": 50321,
114
+ "<|pl|>": 50269,
115
+ "<|ps|>": 50340,
116
+ "<|pt|>": 50267,
117
+ "<|ro|>": 50284,
118
+ "<|ru|>": 50263,
119
+ "<|sa|>": 50344,
120
+ "<|sd|>": 50332,
121
+ "<|si|>": 50322,
122
+ "<|sk|>": 50298,
123
+ "<|sl|>": 50305,
124
+ "<|sn|>": 50324,
125
+ "<|so|>": 50326,
126
+ "<|sq|>": 50317,
127
+ "<|sr|>": 50303,
128
+ "<|su|>": 50357,
129
+ "<|sv|>": 50273,
130
+ "<|sw|>": 50318,
131
+ "<|ta|>": 50287,
132
+ "<|te|>": 50299,
133
+ "<|tg|>": 50331,
134
+ "<|th|>": 50289,
135
+ "<|tk|>": 50341,
136
+ "<|tl|>": 50348,
137
+ "<|tr|>": 50268,
138
+ "<|tt|>": 50351,
139
+ "<|uk|>": 50280,
140
+ "<|ur|>": 50290,
141
+ "<|uz|>": 50337,
142
+ "<|vi|>": 50278,
143
+ "<|yi|>": 50335,
144
+ "<|yo|>": 50325,
145
+ "<|zh|>": 50260
146
+ },
147
+ "language": "hindi",
148
+ "length_penalty": 1.0,
149
+ "max_initial_timestamp_index": 50,
150
+ "max_length": 448,
151
+ "min_length": 0,
152
+ "no_repeat_ngram_size": 0,
153
+ "no_timestamps_token_id": 50363,
154
+ "num_assistant_tokens": 20,
155
+ "num_assistant_tokens_schedule": "constant",
156
+ "num_beam_groups": 1,
157
+ "num_beams": 1,
158
+ "num_return_sequences": 1,
159
+ "output_scores": false,
160
+ "pad_token_id": 50257,
161
+ "prev_sot_token_id": 50361,
162
+ "remove_invalid_values": false,
163
+ "repetition_penalty": 1.0,
164
+ "return_dict_in_generate": false,
165
+ "return_timestamps": false,
166
+ "suppress_tokens": [
167
+ 1,
168
+ 2,
169
+ 7,
170
+ 8,
171
+ 9,
172
+ 10,
173
+ 14,
174
+ 25,
175
+ 26,
176
+ 27,
177
+ 28,
178
+ 29,
179
+ 31,
180
+ 58,
181
+ 59,
182
+ 60,
183
+ 61,
184
+ 62,
185
+ 63,
186
+ 90,
187
+ 91,
188
+ 92,
189
+ 93,
190
+ 359,
191
+ 503,
192
+ 522,
193
+ 542,
194
+ 873,
195
+ 893,
196
+ 902,
197
+ 918,
198
+ 922,
199
+ 931,
200
+ 1350,
201
+ 1853,
202
+ 1982,
203
+ 2460,
204
+ 2627,
205
+ 3246,
206
+ 3253,
207
+ 3268,
208
+ 3536,
209
+ 3846,
210
+ 3961,
211
+ 4183,
212
+ 4667,
213
+ 6585,
214
+ 6647,
215
+ 7273,
216
+ 9061,
217
+ 9383,
218
+ 10428,
219
+ 10929,
220
+ 11938,
221
+ 12033,
222
+ 12331,
223
+ 12562,
224
+ 13793,
225
+ 14157,
226
+ 14635,
227
+ 15265,
228
+ 15618,
229
+ 16553,
230
+ 16604,
231
+ 18362,
232
+ 18956,
233
+ 20075,
234
+ 21675,
235
+ 22520,
236
+ 26130,
237
+ 26161,
238
+ 26435,
239
+ 28279,
240
+ 29464,
241
+ 31650,
242
+ 32302,
243
+ 32470,
244
+ 36865,
245
+ 42863,
246
+ 47425,
247
+ 49870,
248
+ 50254,
249
+ 50258,
250
+ 50358,
251
+ 50359,
252
+ 50360,
253
+ 50361,
254
+ 50362
255
+ ],
256
+ "target_lookbehind": 10,
257
+ "task": "transcribe",
258
+ "task_to_id": {
259
+ "transcribe": 50359,
260
+ "translate": 50358
261
+ },
262
+ "temperature": 1.0,
263
+ "top_k": 50,
264
+ "top_p": 1.0,
265
+ "transformers_version": "5.3.0",
266
+ "typical_p": 1.0,
267
+ "use_cache": true
268
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e7ff135784b97a6359df6fdb7340a678e6b376be4f04c331dd52ad2197083dd
3
+ size 151061672
preprocessor_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "chunk_length": 30,
3
+ "dither": 0.0,
4
+ "feature_extractor_type": "WhisperFeatureExtractor",
5
+ "feature_size": 80,
6
+ "hop_length": 160,
7
+ "n_fft": 400,
8
+ "n_samples": 480000,
9
+ "nb_max_frames": 3000,
10
+ "padding_side": "right",
11
+ "padding_value": 0.0,
12
+ "return_attention_mask": false,
13
+ "sampling_rate": 16000
14
+ }
processor_config.json ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "feature_extractor": {
3
+ "chunk_length": 30,
4
+ "dither": 0.0,
5
+ "feature_extractor_type": "WhisperFeatureExtractor",
6
+ "feature_size": 80,
7
+ "hop_length": 160,
8
+ "n_fft": 400,
9
+ "n_samples": 480000,
10
+ "nb_max_frames": 3000,
11
+ "padding_side": "right",
12
+ "padding_value": 0.0,
13
+ "return_attention_mask": false,
14
+ "sampling_rate": 16000
15
+ },
16
+ "processor_class": "WhisperProcessor"
17
+ }
runs/Mar14_14-23-02_68cebedf7b2a/events.out.tfevents.1773498182.68cebedf7b2a.5147.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60ad0d1fdea92c11a1bb0771abc8c759f0249ba652308d8f8355b0f15b21c8ea
3
+ size 23594
runs/Mar14_14-23-02_68cebedf7b2a/events.out.tfevents.1773503728.68cebedf7b2a.5147.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6987278850a69db45f97c26980ef0b27c03cecca6f2d9d49a3a3de3aa5c2d1e8
3
+ size 406
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": "<|endoftext|>",
5
+ "clean_up_tokenization_spaces": true,
6
+ "eos_token": "<|endoftext|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [
9
+ "<|endoftext|>",
10
+ "<|startoftranscript|>",
11
+ "<|en|>",
12
+ "<|zh|>",
13
+ "<|de|>",
14
+ "<|es|>",
15
+ "<|ru|>",
16
+ "<|ko|>",
17
+ "<|fr|>",
18
+ "<|ja|>",
19
+ "<|pt|>",
20
+ "<|tr|>",
21
+ "<|pl|>",
22
+ "<|ca|>",
23
+ "<|nl|>",
24
+ "<|ar|>",
25
+ "<|sv|>",
26
+ "<|it|>",
27
+ "<|id|>",
28
+ "<|hi|>",
29
+ "<|fi|>",
30
+ "<|vi|>",
31
+ "<|he|>",
32
+ "<|uk|>",
33
+ "<|el|>",
34
+ "<|ms|>",
35
+ "<|cs|>",
36
+ "<|ro|>",
37
+ "<|da|>",
38
+ "<|hu|>",
39
+ "<|ta|>",
40
+ "<|no|>",
41
+ "<|th|>",
42
+ "<|ur|>",
43
+ "<|hr|>",
44
+ "<|bg|>",
45
+ "<|lt|>",
46
+ "<|la|>",
47
+ "<|mi|>",
48
+ "<|ml|>",
49
+ "<|cy|>",
50
+ "<|sk|>",
51
+ "<|te|>",
52
+ "<|fa|>",
53
+ "<|lv|>",
54
+ "<|bn|>",
55
+ "<|sr|>",
56
+ "<|az|>",
57
+ "<|sl|>",
58
+ "<|kn|>",
59
+ "<|et|>",
60
+ "<|mk|>",
61
+ "<|br|>",
62
+ "<|eu|>",
63
+ "<|is|>",
64
+ "<|hy|>",
65
+ "<|ne|>",
66
+ "<|mn|>",
67
+ "<|bs|>",
68
+ "<|kk|>",
69
+ "<|sq|>",
70
+ "<|sw|>",
71
+ "<|gl|>",
72
+ "<|mr|>",
73
+ "<|pa|>",
74
+ "<|si|>",
75
+ "<|km|>",
76
+ "<|sn|>",
77
+ "<|yo|>",
78
+ "<|so|>",
79
+ "<|af|>",
80
+ "<|oc|>",
81
+ "<|ka|>",
82
+ "<|be|>",
83
+ "<|tg|>",
84
+ "<|sd|>",
85
+ "<|gu|>",
86
+ "<|am|>",
87
+ "<|yi|>",
88
+ "<|lo|>",
89
+ "<|uz|>",
90
+ "<|fo|>",
91
+ "<|ht|>",
92
+ "<|ps|>",
93
+ "<|tk|>",
94
+ "<|nn|>",
95
+ "<|mt|>",
96
+ "<|sa|>",
97
+ "<|lb|>",
98
+ "<|my|>",
99
+ "<|bo|>",
100
+ "<|tl|>",
101
+ "<|mg|>",
102
+ "<|as|>",
103
+ "<|tt|>",
104
+ "<|haw|>",
105
+ "<|ln|>",
106
+ "<|ha|>",
107
+ "<|ba|>",
108
+ "<|jw|>",
109
+ "<|su|>",
110
+ "<|translate|>",
111
+ "<|transcribe|>",
112
+ "<|startoflm|>",
113
+ "<|startofprev|>",
114
+ "<|nocaptions|>",
115
+ "<|notimestamps|>"
116
+ ],
117
+ "is_local": false,
118
+ "language": "hindi",
119
+ "model_max_length": 1024,
120
+ "pad_token": "<|endoftext|>",
121
+ "predict_timestamps": false,
122
+ "processor_class": "WhisperProcessor",
123
+ "return_attention_mask": false,
124
+ "task": "transcribe",
125
+ "tokenizer_class": "WhisperTokenizer",
126
+ "unk_token": "<|endoftext|>"
127
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34d3768d5597d6e5a7d63118e80f44059101c56bf60f8f4722ac7e1bcfe7d31f
3
+ size 5329