lighteternal
/

wav2vec2-large-xlsr-53-greek

Automatic Speech Recognition

hf-asr-leaderboard

xlsr-fine-tuning-week

Model card Files Files and versions Community

lighteternal commited on Mar 17, 2021

Commit

bcd0937

·

1 Parent(s): 432c2f1

Update README.md

Files changed (1) hide show

README.md +2 -1

README.md CHANGED Viewed

@@ -138,7 +138,8 @@ Instructions and code to replicate the process are provided in the Fine_Tune_XLS
 | ----------- | ----------- |
 | Training Loss | 0.0287 |
 | Validation Loss | 0.6062 |
-| WER  | 0.4287 |
 Full metrics log here:
 <img src="https://huggingface.co/lighteternal/wav2vec2-large-xlsr-53-greek/raw/main/logs.png" width="600"/>

 | ----------- | ----------- |
 | Training Loss | 0.0287 |
 | Validation Loss | 0.6062 |
+| WER on CommonVoice Test &ast| 0.3960 |
+&ast Reference transcripts were lower-cased and striped of punctuation and special characters.
 Full metrics log here:
 <img src="https://huggingface.co/lighteternal/wav2vec2-large-xlsr-53-greek/raw/main/logs.png" width="600"/>