openai/whisper-large-v3

#105 opened over 1 year ago by

kbuwel

Audio input consists of only 3000. Short-form transcription is activated.no_speech_threshold is set to 0.5, but will be ignored.

#104 opened over 1 year ago by

rizwanishaq

transcribing chinese audio with the this model, the output text lacks punctuation

➕ 5

#103 opened over 1 year ago by

TaoGoblin

Issues with transcription of Burmese audio

#102 opened over 1 year ago by

hanshupe

How can i return both word level and segment together when using hugging face transformer?

➕ 1

#101 opened over 1 year ago by

lilijy

Incoherences in timestamps between chunked and sequential form

👍 13

4

#100 opened over 1 year ago by

vprosadm

How we can use this model to achieve a real-time trans？

4

#99 opened over 1 year ago by

Von-violet

How to get accuracy of transcription from the model?

👍 2

#98 opened almost 2 years ago by

Atulad

Module not found error. No module named GTTS.

#97 opened almost 2 years ago by

BeyondStreamlit

Enhancing Pipeline with Speech Probability for Reduced Hallucination

#96 opened almost 2 years ago by

rizwanishaq

Rename README.md to persian

#95 opened almost 2 years ago by

Zabs

OpenAI Whisper Support Urdu (Pakistan) language?

#94 opened almost 2 years ago by

AamirFarooq

How to mention lanuage parameter on inference api

#93 opened almost 2 years ago by

aitransync

Download and Load model on local system.

#92 opened almost 2 years ago by

RebelloAlbina

How to save the loss value for each step during the training process?

#91 opened almost 2 years ago by

zhouwen999

Auto speech/languages detection in Real Time streaming?

👀 1

#89 opened almost 2 years ago by

sabys

not transcribing to english

#88 opened almost 2 years ago by

aitransync

Does it support Korean translation and speech? :)

#87 opened almost 2 years ago by

JinPark

Transcript an Spanish audio

4

#86 opened almost 2 years ago by

Andrews99

is it possible to access the transcript result in batches after each chunk has finished?

#85 opened almost 2 years ago by

hanifanggawi

how to download model and load model and use it

👀 1

#84 opened almost 2 years ago by

r5avindra

[AUTOMATED] Model Memory Requirements

🔥 👍 6

#83 opened almost 2 years ago by

model-sizer-bot

Output Discrepancy

😔 1

#82 opened almost 2 years ago by

eBisw

Transcription and Translation In the same call

#81 opened almost 2 years ago by

saalnlp

model in closed network

👍 1

#78 opened almost 2 years ago by

iamwhoiamm

Trouble shooting local inference on whisper

#77 opened almost 2 years ago by

RESOLVER101757

The new Longform transcription method

#76 opened almost 2 years ago by

deep-intel

Upload vocab.json

#74 opened almost 2 years ago by

smerchi

How to adapt for low resource language?

9

#73 opened almost 2 years ago by

Imran1

Problems with AutoProcessor

#72 opened almost 2 years ago by

Kwang442

Suddenly all my transcriptions are in English

👍 6

11

#71 opened almost 2 years ago by

WWCF

Transcription in different languages for Punjabi audio

#67 opened almost 2 years ago by

jssaluja

I want to use Whisper on a piece of hardware

#66 opened almost 2 years ago by

Avinier

How to fix "TypeError: expected str, bytes or os.PathLike object, not NoneType" when specifying the local whisper model

#65 opened almost 2 years ago by

BenjaminChu

Speaker Embedding

👍 4

#64 opened almost 2 years ago by

bertrand-fournel

whisper jax diarization Icelandic

#62 opened about 2 years ago by

Dondada79

Translating English Audio Into Spanish Text

#61 opened about 2 years ago by

stvnchnsn

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

#60 opened about 2 years ago by

dkincaid

Passing parameters to the model deployed on HF Inference Endpoints

#59 opened about 2 years ago by

dkincaid

Does whisper-large-v3 work on Sagemaker?

#58 opened about 2 years ago by

dkincaid

Which File Shall I Download from The Files and Versions

#57 opened about 2 years ago by

BenjaminChu

Transcribing multiple languages in single audio file

#56 opened about 2 years ago by

supercharge19

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

👍 1

#55 opened about 2 years ago by

rizwanishaq

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

#54 opened about 2 years ago by

unk1911

changed use_flash_attention_2=True to attn_implementation="flash_attention_2"

#53 opened about 2 years ago by

macadeliccc

Whisper parameters?

👍 1

#52 opened about 2 years ago by

Megatron17

Whisper large v3 can not recognize speech after Fine-Tune

#51 opened about 2 years ago by

bardenthenry

how download large version?

#50 opened about 2 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?