edugp
/

wav2vec2-xls-r-300m-36-tokens-with-lm-es

Automatic Speech Recognition

generated_from_trainer

hf-asr-leaderboard

robust-speech-event

Inference Endpoints

Model card Files Files and versions Community

edugp commited on Feb 4, 2022

Commit

b0739e8

•

1 Parent(s): d1085ba

Update README.md

Files changed (1) hide show

README.md +4 -5

README.md CHANGED Viewed

@@ -17,10 +17,10 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 0.09223274877376873
        - name: Test CER
          type: cer
-         value: 0.03065986931858979
 ---
 # Wav2Vec2-xls-r-300m-36-chars-es
@@ -31,9 +31,8 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
 It achieves the following results on the evaluation set:
-- Loss: 0.2362
-- Wer: 0.1118
 ## Model description
 More information needed

     metrics:
        - name: Test WER
          type: wer
+         value: 0.08677014042867702
        - name: Test CER
          type: cer
+         value: 0.02810974186831335
 ---
 # Wav2Vec2-xls-r-300m-36-chars-es
 This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
 It achieves the following results on the evaluation set:
+- Wer: 0.0868
+- Cer: 0.0281
 ## Model description
 More information needed