openai/whisper-large-v3

Whisper only transcribes the English words and ignores the rest of the Spanish audio

#220 opened 6 days ago by

davera-017

Upload Новая запись 5.m4a

#219 opened 9 days ago by

Artem2308

bot

#217 opened 12 days ago by

Dieselcenter

*   Title: Getting 410 Gone error on all Whisper models via Inference API - Are they available on free tier?

#216 opened 25 days ago by

EzekielSolutions

Request: DOI

#215 opened about 2 months ago by

MrAaronJR

Upload Lilla 1.m4a

#213 opened 3 months ago by deleted

Upload RingVideo_20250907_162127_ENHANCED.wav

#212 opened 3 months ago by

murdock65

Upload RingVideo_20250907_162127_ENHANCED.wav

#211 opened 3 months ago by

murdock65

Upload Flintstones Unheard.mp3

🔥 1

#210 opened 3 months ago by

Xeeeefi

Upload 20250821_100154_0757866036.wav

#209 opened 4 months ago by

Amani1310

deneme

#208 opened 4 months ago by

NNEMES1SS

Code Switching using Whisper-large-v3

#207 opened 4 months ago by

indrasn0wal

Upload New Recording 4.m4a

#206 opened 4 months ago by

Enwallace

Can Deepspeed ZeRO3 be used for Sharding with Whisper-large-v3?

#204 opened 5 months ago by

PhoenixAxis

Fix example usage

👍 1

#202 opened 5 months ago by

bezzam

RuntimeError: Trying to backward through the graph a second time

👍 6

8

#201 opened 5 months ago by

Sarwg

语音模型

#200 opened 5 months ago by

skyhe666

Incorrect feature_size in preprocessor_config.json (should be 80)

1

#199 opened 5 months ago by

alexg1802

Upload 60fps Audio 2_45.wav

#198 opened 5 months ago by

11fred11

Audio refinning

#197 opened 6 months ago by

Baalbatos

BTS

2

#196 opened 6 months ago by

Birima

Upload AUDIO.mp3.mp3

#195 opened 6 months ago by

OJG15

Video format problem.

#194 opened 6 months ago by

pantorn

Word Timestamps error: RuntimeError: The expanded size of the tensor (69) must match the existing size (72) at non-singleton dimension 1. Target sizes: [1, 69]. Tensor sizes: [72] whisper word.

👍 1

2

#193 opened 6 months ago by

muaviyaijaz123

Muniyan

#192 opened 6 months ago by

Orion14

two warnings

#190 opened 7 months ago by

youarecode

whisper large v3 finetuning using our own dataset

1

#189 opened 8 months ago by

rifasca

Upload New Recording 3.m4a

#188 opened 8 months ago by

Hellometo

Why does a tiny silence at the start of my audio change Whisper’s transcription?

#187 opened 8 months ago by

dylanewbie

Upload 10 files

#186 opened 9 months ago by

Usshhaa

Whisper openai vs hugging face question

#185 opened 9 months ago by

Sin2pi

what are the limits for Whisper here?

#184 opened 9 months ago by

vendeza

Rename README.md to README.mdwas könnte die Ursache für Kopf- und Nackenschmerzen Blutdruckschwankungen Papillenödem und übelkeit sein

1

#183 opened 9 months ago by

Oskar000

getting an error trying to extract word-level timestamps

#182 opened 9 months ago by

SphinxKing

Download error. Manually specifying the catalog with models.

#181 opened 10 months ago by

Incrediblecat

Can I use a CLI of it? Just found this project, no experience with AI, just want to convert audio speech to text

#180 opened 10 months ago by

vitaly-zdanevich

Upload AUD-20250217-WA0001.m4a

#179 opened 10 months ago by

Gerald02

Extract words with timestamps

#178 opened 10 months ago by

codingyash

Working example on Mac M-series

#177 opened 10 months ago by

pajikos

[badcase report] observe significant recognition errors on an example of libri_light dataset.

#176 opened 10 months ago by

lawlict

Upload audio1477337879.m4a

#175 opened 10 months ago by

Elena9292

Multi task finetuning (transcribe and translate)

#174 opened 11 months ago by

Phil-AB

SegmentAnything Ultra V2

1

#173 opened 12 months ago by

didi4725

How to freeze layers and fine tuning

2

#172 opened 12 months ago by

Sarwg

Challenges in Distinguishing Similar Phonemes (e.g., 'B' and 'V') in License Plate Speech Recognition Using Whisper-Large Model

#171 opened 12 months ago by

dylanewbie

Inference on fine-tuned whisper-large-v3 is not working, but is working on pre-trained model and whisper-medium

#169 opened about 1 year ago by

ivabojic

🚩 Report: Not working

#168 opened about 1 year ago by

ednsinf

Speech recognition broken down by speakers

👀 1

6

#167 opened about 1 year ago by

tur0kmag

the chinese training data of the model is contaminated

2

#165 opened about 1 year ago by

bookwoods123

Specify language for transcribing with HuggingFace API

7

#164 opened about 1 year ago by

mikealexx

Whisper only transcribes the English words and ignores the rest of the Spanish audio

Upload Новая запись 5.m4a

bot

* Title: Getting 410 Gone error on all Whisper models via Inference API - Are they available on free tier?

Request: DOI

Upload Lilla 1.m4a

Upload RingVideo_20250907_162127_ENHANCED.wav

Upload RingVideo_20250907_162127_ENHANCED.wav

Upload Flintstones Unheard.mp3

Upload 20250821_100154_0757866036.wav

deneme

Code Switching using Whisper-large-v3

Upload New Recording 4.m4a

Can Deepspeed ZeRO3 be used for Sharding with Whisper-large-v3?

Fix example usage

RuntimeError: Trying to backward through the graph a second time

语音模型

Incorrect feature_size in preprocessor_config.json (should be 80)

Upload 60fps Audio 2_45.wav

Audio refinning

BTS

Upload AUDIO.mp3.mp3

Video format problem.

Word Timestamps error: RuntimeError: The expanded size of the tensor (69) must match the existing size (72) at non-singleton dimension 1. Target sizes: [1, 69]. Tensor sizes: [72] whisper word.

Muniyan

two warnings

whisper large v3 finetuning using our own dataset

Upload New Recording 3.m4a

Why does a tiny silence at the start of my audio change Whisper’s transcription?

Upload 10 files

Whisper openai vs hugging face question

what are the limits for Whisper here?

Rename README.md to README.mdwas könnte die Ursache für Kopf- und Nackenschmerzen Blutdruckschwankungen Papillenödem und übelkeit sein

getting an error trying to extract word-level timestamps

Download error. Manually specifying the catalog with models.

Can I use a CLI of it? Just found this project, no experience with AI, just want to convert audio speech to text

Upload AUD-20250217-WA0001.m4a

Extract words with timestamps

Working example on Mac M-series

[badcase report] observe significant recognition errors on an example of libri_light dataset.

Upload audio1477337879.m4a

Multi task finetuning (transcribe and translate)

SegmentAnything Ultra V2

How to freeze layers and fine tuning

Challenges in Distinguishing Similar Phonemes (e.g., 'B' and 'V') in License Plate Speech Recognition Using Whisper-Large Model

Inference on fine-tuned whisper-large-v3 is not working, but is working on pre-trained model and whisper-medium

🚩 Report: Not working

Speech recognition broken down by speakers

the chinese training data of the model is contaminated

Specify language for transcribing with HuggingFace API

*   Title: Getting 410 Gone error on all Whisper models via Inference API - Are they available on free tier?