openai/whisper-large-v2

using WhisperTokenizer to generate input for onnx inference

#118 opened about 2 months ago by

SantoshHF

Expose metadata link to next version of the model

#117 opened 4 months ago by

davanstrien

[AUTOMATED] Model Memory Requirements

#116 opened 7 months ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#115 opened 7 months ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#114 opened 7 months ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#113 opened 7 months ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#112 opened 7 months ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#111 opened 7 months ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#110 opened 7 months ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#109 opened 7 months ago by

model-sizer-bot

[AUTOMATED] Model Memory Requirements

#108 opened 7 months ago by

model-sizer-bot

return Timestamps="word" not working correctly

#106 opened 10 months ago by

DShah-11

Upload Tắt đèn - Chương I - Ngô Tất Tố.mp3

#105 opened 11 months ago by

123aaas

Using a fine-tuned model for the pipeline for the long-form transcription

#104 opened 11 months ago by

Hossep

Difference in Transcription Quality Between Local Whisper Large V2 and Model Card Inference API

#103 opened 11 months ago by

nkanaka1

Why are the V2 weights twice the size as V3?

#102 opened 12 months ago by

stri8ted

Issue with special tokens after the last update of some Whisper's files

#101 opened 12 months ago by

trscmn

Request: DOI

#99 opened about 1 year ago by

Coletomyo

add link for whisper large v3 to the readme

#98 opened about 1 year ago by

iitsg

question about whisper feature extractor

#97 opened about 1 year ago by

freashpearyoon

Adding ONNX file of this model

#96 opened about 1 year ago by

nirajkale30

� in the predictions

#94 opened about 1 year ago by

golesheed

Upload WhisperForConditionalGeneration

#93 opened about 1 year ago by

denzim

Upload WhisperForConditionalGeneration

#92 opened about 1 year ago by

denzim

Update english only / multilingual table

#91 opened about 1 year ago by

jcrisch

Endpoint waiting to be scheduled?

2

#90 opened about 1 year ago by

seeknndestroy

How to finetune on Kaggle TPU

8

#89 opened about 1 year ago by

LukeJacob2023

whisper v3

#88 opened over 1 year ago by

amgadhasan

Whisper with Torchserve

#87 opened over 1 year ago by

rbgreenway

WhisperProcessor.from_pretrained Error

#86 opened over 1 year ago by

viyoung

Is WhisperForAudioClassification can implements Audio Classification like Yamnet(based on AudioSet), in theory? thanks

#85 opened over 1 year ago by

thelou1s

whisper-large-v2

#83 opened over 1 year ago by

pingqw

whisper

#82 opened over 1 year ago by

pingqw

How does OpenAI Whisper's medium.en, large or whisper-large-v2 compare in terms of word error rate?

1

#79 opened over 1 year ago by

Franck-Dernoncourt

Fine-tuning for two languages

7

#78 opened over 1 year ago by

artyomboyko

How can i seperate output words between chunks?

2

#77 opened over 1 year ago by

ericchen

Finetuning Whisper for translate task

#76 opened over 1 year ago by

lypspeech

Using HuggingfaceJS inference API, is it possible to get the "returnTimestamps: true"

#75 opened over 1 year ago by

zhefciad

About length of audio input to the model

2

#73 opened over 1 year ago by

sanjitaa

About length of audio

1

#72 opened over 1 year ago by

RaysDipesh

Correct added token ids

#71 opened over 1 year ago by

sanchit-gandhi

model failing to transcribe but working fine for translation

1

#70 opened over 1 year ago by

atulyaatul

[AUTOMATED] Model Memory Requirements

#69 opened over 1 year ago by

model-sizer-bot

Error 503

1

#68 opened over 1 year ago by

VishnuBhanderi

Will spell corrector on whisper output be worth it?

1

#62 opened over 1 year ago by

MightyStudent

Large audio file (more then 2 hours)

1

#59 opened over 1 year ago by

jonfv

Upload 14 ago. 10.30 p. m..aac

#58 opened over 1 year ago by

Deybin

Using no_speech token to determine silent segments

#56 opened over 1 year ago by

Yashadd

Can we use this model to transfer learning for CPR waveform data ??

#53 opened over 1 year ago by

itzzsayeed

How to finetune whisper model for language which is not supported by WhisperTokenizer

#52 opened over 1 year ago by

nathanhunt

using WhisperTokenizer to generate input for onnx inference

Expose metadata link to next version of the model

[AUTOMATED] Model Memory Requirements

[AUTOMATED] Model Memory Requirements

[AUTOMATED] Model Memory Requirements

[AUTOMATED] Model Memory Requirements

[AUTOMATED] Model Memory Requirements

[AUTOMATED] Model Memory Requirements

[AUTOMATED] Model Memory Requirements

[AUTOMATED] Model Memory Requirements

[AUTOMATED] Model Memory Requirements

return Timestamps="word" not working correctly

Upload Tắt đèn - Chương I - Ngô Tất Tố.mp3

Using a fine-tuned model for the pipeline for the long-form transcription

Difference in Transcription Quality Between Local Whisper Large V2 and Model Card Inference API

Why are the V2 weights twice the size as V3?

Issue with special tokens after the last update of some Whisper's files

Request: DOI

add link for whisper large v3 to the readme

question about whisper feature extractor

Adding ONNX file of this model

� in the predictions

Upload WhisperForConditionalGeneration

Upload WhisperForConditionalGeneration

Update english only / multilingual table

Endpoint waiting to be scheduled?

How to finetune on Kaggle TPU

whisper v3

Whisper with Torchserve

WhisperProcessor.from_pretrained Error

Is WhisperForAudioClassification can implements Audio Classification like Yamnet(based on AudioSet), in theory? thanks

whisper-large-v2

whisper

How does OpenAI Whisper's medium.en, large or whisper-large-v2 compare in terms of word error rate?

Fine-tuning for two languages

How can i seperate output words between chunks?

Finetuning Whisper for translate task

Using HuggingfaceJS inference API, is it possible to get the "returnTimestamps: true"

About length of audio input to the model

About length of audio

Correct added token ids

model failing to transcribe but working fine for translation

[AUTOMATED] Model Memory Requirements

Error 503

Will spell corrector on whisper output be worth it?

Large audio file (more then 2 hours)

Upload 14 ago. 10.30 p. m.​.aac

Using no_speech token to determine silent segments

Can we use this model to transfer learning for CPR waveform data ??

How to finetune whisper model for language which is not supported by WhisperTokenizer

Upload 14 ago. 10.30 p. m..aac