facebook
/
wav2vec2-base-960h
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
Patrick von Platen 2021-02-08 17:10:43 +00:00 committed by huggingface-web
parent 3eb23cb979
commit 671b8e7c54
1 changed files with 2 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -62,7 +62,7 @@ To transcribe audio files the model can be used as a standalone acoustic model a
transcription = tokenizer.batch_decode(predicted_ids)
```
## Evalution
## Evaluation
This code snippet shows how to evaluate **facebook/wav2vec2-base-960h** on LibriSpeech's "clean" and "other" test data.
@ -103,4 +103,4 @@ print("WER:", wer(result["text"], result["transcription"]))
| "clean" | "other" |
|---|---|
| 4.1 | |
| 4.1 | 10.0 |