Resources

Speaker Embedding

👍 4

#64 opened almost 3 years ago by

bertrand-fournel

whisper jax diarization Icelandic

#62 opened almost 3 years ago by

Dondada79

Translating English Audio Into Spanish Text

#61 opened almost 3 years ago by

stvnchnsn

Error with word level timestamps - ValueError: set return_segments=True

#60 opened almost 3 years ago by

dkincaid

Passing parameters to the model deployed on HF Inference Endpoints

#59 opened almost 3 years ago by

dkincaid

Does whisper-large-v3 work on Sagemaker?

#58 opened almost 3 years ago by

dkincaid

Which File Shall I Download from The Files and Versions

#57 opened almost 3 years ago by

BenjaminChu

Transcribing multiple languages in single audio file

#56 opened almost 3 years ago by

supercharge19

Is there any way we can get no_speech_probability from the pipeline?

👍 1

#55 opened almost 3 years ago by

rizwanishaq

how to handle input audio files with either white noise or general noise and no speech

#54 opened almost 3 years ago by

unk1911

changed use_flash_attention_2=True to attn_implementation="flash_attention_2"

#53 opened almost 3 years ago by

macadeliccc

Whisper parameters?

👍 1

#52 opened almost 3 years ago by

Megatron17

Whisper large v3 can not recognize speech after Fine-Tune

#51 opened almost 3 years ago by

bardenthenry

how download large version?

#50 opened almost 3 years ago by

Timnorth

I've noticed that Uyghur language is not available. Is it possible to add the Uyghur (ug) dataset from the Mozilla Foundation's Common Voice 13.0 for training?

#48 opened almost 3 years ago by

almjanx

is parallel processing possible with DLC Deployement?

#47 opened almost 3 years ago by

SharatChandra

Error: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED

#46 opened almost 3 years ago by

duzm

Update README.md

#44 opened almost 3 years ago by

Mucahit01

Training for translation

👍 1

#43 opened almost 3 years ago by

tirtohadi

Whisper-Large-V3 does not work with explicit use of dtype which is given in config.json

#42 opened almost 3 years ago by

ait-paca

Update README.md

#41 opened almost 3 years ago by

joey1895

What azure compute instance will work?

#40 opened almost 3 years ago by

Jayantabasumatary1

Getting pipeline time estimate

👍 1

#39 opened almost 3 years ago by

wwilcz

pull

#37 opened almost 3 years ago by

zach106

how to evaluate use model-00001-of-00002.safetensors and model-00002-of-00002.safetensors

#36 opened almost 3 years ago by

andyweiqiu

Does anyone know how to tag the speaker with Whisper?

#35 opened almost 3 years ago by

Shaunnnnn

List of Supported Input Parameters?

👍 2

#34 opened almost 3 years ago by

souvik0306

Understands Finnish well

👍 1

#33 opened almost 3 years ago by

Ukuli

whisper outputs non stop no no no

#32 opened almost 3 years ago by

rizwanishaq

Word timestamps and "return_language" at the same time

#31 opened almost 3 years ago by

Oscaarjs

Batched files with different languages

#30 opened almost 3 years ago by

Oscaarjs

Wrong Suffix after Downloading

#29 opened almost 3 years ago by

seriphus

Add TF weights

#28 opened almost 3 years ago by

vlad-skripniuk

Setting whisper-specific options in pipeline

👍 4

#26 opened almost 3 years ago by

MichalQU

no_speech_prob in pipeline?

#22 opened almost 3 years ago by

rizwanishaq

language='cantonese' error

#21 opened almost 3 years ago by

Boxp

Speculative Decoding Snippet Not Working

#20 opened almost 3 years ago by

nateraw

Hallucination / repetition

#19 opened almost 3 years ago by

persundstrom

can i use this free ?

#18 opened almost 3 years ago by

AamirFarooq

How to get the language in default mode

#15 opened almost 3 years ago by

nastasev

Error with word level timestamps

#12 opened almost 3 years ago by

souvik0306

How to get Word and Verbose level transcription?

#11 opened almost 3 years ago by

souvik0306

Translate using the API

👍 3

#10 opened almost 3 years ago by

SharatChandra

Error when running a model inference

👍 3

#8 opened almost 3 years ago by

agonben23

TokenizerFast with tokenizer.json

#7 opened almost 3 years ago by

vubiqus

Why float16? Why not Float32

#4 opened almost 3 years ago by

ctranslate2-4you

Currently working on finetuning dataset for japanese anime speech

👍 2

#3 opened almost 3 years ago by

joujiboi