jbetker
/
wav2vec2-large-robust-ft-libritts-voxpopuli
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
James Betker 2022-02-25 19:07:57 +00:00 committed by huggingface-web
parent eaf8dc21e3
commit 33e5835aad
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -6,4 +6,6 @@ The model gets a respectable WER of 4.45% on the librispeech validation set. The
Since the model was fine-tuned on clean audio, it is not well-suited for noisy audio like CommonVoice (though I may upload a checkpoint for that soon too). It still does pretty good, though. Since the model was fine-tuned on clean audio, it is not well-suited for noisy audio like CommonVoice (though I may upload a checkpoint for that soon too). It still does pretty good, though.
The vocabulary is uploaded to the model hub as well `jbetker/tacotron_symbols`. The vocabulary is uploaded to the model hub as well `jbetker/tacotron_symbols`.
Check out my speech transcription script repo, [ocotillo](https://github.com/neonbjb/ocotillo) for usage examples: https://github.com/neonbjb/ocotillo