Commits · ithuan/formosan-f5-tts

SonarCloud Code Scan修正 (#3)

b5b4fe3
verified

txya900619

Sing-hong commited on 21 days ago

fix: regex for language extraction

aa103f3

txya900619 commited on Oct 21

style: update CSS for textarea border and add class for text-only elements

74be43a

txya900619 commited on Oct 20

feat: enhance UI/UX and fix custom_speaker_ref_text_input empty bug

d476512

txya900619 commited on Oct 19

refactor: update tab labels and button texts for clarity in speaker selection steps

1bbfe6d

txya900619 commited on Sep 15

fix: update button tooltip text for special characters

341059a

txya900619 commited on Aug 19

feat: change layout for ithuan demo page

31852bc

txya900619 commited on Aug 19

fix: set default value for remove_silence parameter in infer function

5e38562

txya900619 commited on Aug 19

feat: add dynamic example loading based on language selection

a731f03

txya900619 commited on Aug 18

feat: replace torchaudio with torchcodec for audio decoding

29c7e98

txya900619 commited on Aug 18

feat: language show all language in g2p_object and change to dropdown

039f399

txya900619 commited on May 29

feat: add example contain :

ae54386

txya900619 commited on May 23

feat: add all-formosan-step-432640 model and use ref_wav lower than 12 sec

be9c172

txya900619 commited on May 23

feat: enhance load_model function with old and dtype args, update example for new g2p csv

14f96db

txya900619 commited on May 23

feat: use speed in infer_process

c3d752c
verified

txya900619 commited on May 19

fix: fix old model after f5-tts v1.0

f357dd6

txya900619 commited on May 19

feat: add load_ema arg to load_f5tts function

6c327d1
verified

txya900619 commited on May 19

feat: ignore_punctuation and ipa_with_ng to false

43389f1
verified

txya900619 commited on May 19

feat: add language selection and update IPA processing to support multiple languages

d992f07

txya900619 commited on Feb 17

feat: update reference audio files and add new wav files

ed43fae

txya900619 commited on Feb 17

fix: correct punctuation in reference audio transcriptions

e36be83

txya900619 commited on Feb 17

feat: change ipa parser to support ŋ

443b650

txya900619 commited on Feb 17

fix: remove dialect

f06873a

txya900619 commited on Feb 12

feat: add app.py

0c074b9

txya900619 commited on Feb 12

Spaces:

Duplicated from united-link/formosan-f5-tts

ithuan
/

formosan-f5-tts

Paused

Commit History

SonarCloud Code Scan修正 (#3)

b5b4fe3
verified

fix: regex for language extraction

aa103f3

style: update CSS for textarea border and add class for text-only elements

74be43a

feat: enhance UI/UX and fix custom_speaker_ref_text_input empty bug

d476512

refactor: update tab labels and button texts for clarity in speaker selection steps

1bbfe6d

fix: update button tooltip text for special characters

341059a

feat: change layout for ithuan demo page

31852bc

fix: set default value for remove_silence parameter in infer function

5e38562

feat: add dynamic example loading based on language selection

a731f03

feat: replace torchaudio with torchcodec for audio decoding

29c7e98

feat: language show all language in g2p_object and change to dropdown

039f399

feat: add example contain :

ae54386

feat: add all-formosan-step-432640 model and use ref_wav lower than 12 sec

be9c172

feat: enhance load_model function with old and dtype args, update example for new g2p csv

14f96db

feat: use speed in infer_process

c3d752c
verified

fix: fix old model after f5-tts v1.0

f357dd6

feat: add load_ema arg to load_f5tts function

6c327d1
verified

feat: ignore_punctuation and ipa_with_ng to false

43389f1
verified

feat: add language selection and update IPA processing to support multiple languages

d992f07

feat: update reference audio files and add new wav files

ed43fae

fix: correct punctuation in reference audio transcriptions

e36be83

feat: change ipa parser to support ŋ

443b650

fix: remove dialect

f06873a

feat: add app.py

0c074b9

Commit History

SonarCloud Code Scan修正 (#3) b5b4fe3 verified

fix: regex for language extraction aa103f3

style: update CSS for textarea border and add class for text-only elements 74be43a

feat: enhance UI/UX and fix custom_speaker_ref_text_input empty bug d476512

refactor: update tab labels and button texts for clarity in speaker selection steps 1bbfe6d

fix: update button tooltip text for special characters 341059a

feat: change layout for ithuan demo page 31852bc

fix: set default value for remove_silence parameter in infer function 5e38562

feat: add dynamic example loading based on language selection a731f03

feat: replace torchaudio with torchcodec for audio decoding 29c7e98

feat: language show all language in g2p_object and change to dropdown 039f399

feat: add example contain : ae54386

feat: add all-formosan-step-432640 model and use ref_wav lower than 12 sec be9c172

feat: enhance load_model function with old and dtype args, update example for new g2p csv 14f96db

feat: use speed in infer_process c3d752c verified

fix: fix old model after f5-tts v1.0 f357dd6

feat: add load_ema arg to load_f5tts function 6c327d1 verified

feat: ignore_punctuation and ipa_with_ng to false 43389f1 verified

feat: add language selection and update IPA processing to support multiple languages d992f07

feat: update reference audio files and add new wav files ed43fae

fix: correct punctuation in reference audio transcriptions e36be83

feat: change ipa parser to support ŋ 443b650

fix: remove dialect f06873a

feat: add app.py 0c074b9

SonarCloud Code Scan修正 (#3)

b5b4fe3
verified

fix: regex for language extraction

aa103f3

style: update CSS for textarea border and add class for text-only elements

74be43a

feat: enhance UI/UX and fix custom_speaker_ref_text_input empty bug

d476512

refactor: update tab labels and button texts for clarity in speaker selection steps

1bbfe6d

fix: update button tooltip text for special characters

341059a

feat: change layout for ithuan demo page

31852bc

fix: set default value for remove_silence parameter in infer function

5e38562

feat: add dynamic example loading based on language selection

a731f03

feat: replace torchaudio with torchcodec for audio decoding

29c7e98

feat: language show all language in g2p_object and change to dropdown

039f399

feat: add example contain :

ae54386

feat: add all-formosan-step-432640 model and use ref_wav lower than 12 sec

be9c172

feat: enhance load_model function with old and dtype args, update example for new g2p csv

14f96db

feat: use speed in infer_process

c3d752c
verified

fix: fix old model after f5-tts v1.0

f357dd6

feat: add load_ema arg to load_f5tts function

6c327d1
verified

feat: ignore_punctuation and ipa_with_ng to false

43389f1
verified

feat: add language selection and update IPA processing to support multiple languages

d992f07

feat: update reference audio files and add new wav files

ed43fae

fix: correct punctuation in reference audio transcriptions

e36be83

feat: change ipa parser to support ŋ

443b650

fix: remove dialect

f06873a

feat: add app.py

0c074b9