openai
/

whisper-medium

Automatic Speech Recognition

hf-asr-leaderboard

Eval Results (legacy)

Model card Files Files and versions

Resources

View closed (24)

Finetuned medium on single GPU but can't train on 2 GPUs. (RTX 3060)

#40 opened over 1 year ago by

OSErrorOSErrorOSErrorOSError: [Errno 28] No space left on device

#39 opened over 1 year ago by

Update README.md

#38 opened about 2 years ago by

[AUTOMATED] Model Memory Requirements

#37 opened about 2 years ago by

model-sizer-bot

Adding ONNX file of this model

#35 opened over 2 years ago by

karthikeyan-cse

VOLUME

#34 opened over 2 years ago by

Fine Tuning Results in Empty Predictions

#33 opened over 2 years ago by

The same audio. Why are the results on Hugging Face different from the results of the model on GitHub?

#31 opened over 2 years ago by

[AUTOMATED] Model Memory Requirements

#30 opened over 2 years ago by

model-sizer-bot

Is to possible to use Whisper pytorch model with different dtype than the entry in config.json?

#28 opened over 2 years ago by

Question about fine-tuning

#27 opened over 2 years ago by

Correct added token ids

#26 opened over 2 years ago by

About using whisper model as API

#25 opened over 2 years ago by

Inference api other languages

#19 opened almost 3 years ago by

openai/whisper-medium used in pipeline automatically translates to english

#17 opened about 3 years ago by

private-langsource

IndexError while using with language "japanese" (transcribe)

#16 opened about 3 years ago by