openai
/

whisper-large

Automatic Speech Recognition

hf-asr-leaderboard

Eval Results (legacy)

Model card Files Files and versions

Update config for automatic language detection

#19

by ArthurZ HF Staff - opened Jan 20, 2023

base: refs/heads/main

←

from: refs/pr/19

Discussion Files changed

This should allow the model to detect the language by running a forward loop and filling with the <lan> lang token

Update config for automatic language detectionba27f33e

cc @sanchit-gandhi

Logic sounds good to me! Although not sure we can have None in a json - has to be null right? c.f. https://huggingface.co/openai/whisper-large/blob/main/tokenizer_config.json#L23

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

Cannot merge

This branch has merge conflicts in the following files:

config.json

· Sign up or log in to comment