openai/whisper · Discussions

#125 opened about 2 months ago by

teretrave

How to estimate the GPU memory needed to finetune whisper large model?

#124 opened 2 months ago by

MonoLeon

Error

3

#123 opened 2 months ago by

Tinabina

How to fine tuning with timestamps

#122 opened 3 months ago by

deepdml

🚩 Report: ERROR: [youtube] <film ID>: Sign in to confirm you’re not a bot. This helps protect our community. Learn more

7

#121 opened 3 months ago by

yuuyang

wikarena

#120 opened 4 months ago by

WIKARENA

builtins.ValueError: None

#119 opened 4 months ago by

Superchik

🚩 Report: Not working

#118 opened 7 months ago by

Qucculi1999

Is it possible to silence non-verbal parts of an audio?

#116 opened 8 months ago by

rdx2k7

whisper fine tuning question

#115 opened 8 months ago by

spawar

Any luck fine tuning for multiple languages?

#113 opened 9 months ago by

gcasey2

How to Generate a .mlmodel File for Apple's CoreML Framework ?

#112 opened 11 months ago by

Garry1234

Error regardless of file

#111 opened 11 months ago by

Billythefish

Multilingual distribution of Whisper training data

#110 opened 11 months ago by

rdzotz

Test

#108 opened 11 months ago by

osanseviero

Whisper Finetuning - Validation loss is increasing but WER is Decreasing

#107 opened 11 months ago by

anahar

How can I use WhisperAI now? I see that everything's changed

#104 opened 11 months ago by

Snakecharmer

🚩 Report: Not working

#103 opened 11 months ago by

emirvmendoza

Can someone turn this into a chrome extension?

#102 opened 11 months ago by

guym88

Whisper return old output

#101 opened 11 months ago by

arsen7076

performance drops and Hallucination Increases after finetuning the Whisper-small

#100 opened 11 months ago by

anahar

test

#99 opened about 1 year ago by

wuzhanliai21

How to get loss function value for a given audio and text pair

#97 opened about 1 year ago by

souraj

Whisper fine-tuning questions

#96 opened about 1 year ago by

kangblue

Real world recording example in case you are collecting a validation dataset

#95 opened about 1 year ago by

Hobson

I have some issue with getting the write input shape for fine tuning whisper AI

#94 opened over 1 year ago by

pedramaa

I am recording to the microphone

#92 opened over 1 year ago by

freddyaboulton

Upload Продающая консультация.mp4

#91 opened over 1 year ago by

YanaRedsun

Fine-tuning Whisper in more than one language

#90 opened over 1 year ago by

andrespm

Fine-tunining Whisper models for shorter audio segments

#89 opened over 1 year ago by

Malishevsky

Phoneme recognition

#86 opened over 1 year ago by

dg96

あ

#83 opened over 1 year ago by

nagase2

Whisper crashes frequently

#82 opened over 1 year ago by

KamiMadara

Multilingual transcription: howto w/o specifying language?

3

#81 opened over 1 year ago by

sanjaymk908

accuracy issues with retrained tiny model for marathi numbers

#80 opened over 1 year ago by

SameerMahajan

added column not getting saved in dataset

#78 opened over 1 year ago by

SameerMahajan

Even when the speakers starts talking after 10 sec, Whisper make the first timestamp to start at sec 0. How could I change that?

#77 opened over 1 year ago by

romain130492

Can Whisper be used for real-time speech to text?

11

#76 opened over 1 year ago by

ImagineThis

Fine-tune Whisper on a Local Custom dataset

#75 opened over 1 year ago by

hamza94

Distinguishing between speech and non speech

#74 opened over 1 year ago by

CarelessWhisperer

useWhisper a React Hook for OpenAI Whisper API

#73 opened over 1 year ago by

chengsokdara

Time-codes from whisper

5

#71 opened over 1 year ago by

EranML

wagahai

#68 opened almost 2 years ago by

wasao238

issues working with marathi numbers

35

#66 opened almost 2 years ago by

SameerMahajan

My Dutch-Whisper experiment.

#65 opened almost 2 years ago by

Arjanneke

adding new tokens to the new fine-tune model

#64 opened almost 2 years ago by

Santi69

fine-tune whisper with CPU