update eval

README.md

@@ -22,16 +22,16 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 23.60
+         value: 21.05
        - name: Test CER
          type: cer
-         value: 9.93
+         value: 8.44
        - name: Test WER (+LM)
          type: wer
-         value: 19.58
+         value: 17.31
        - name: Test CER (+LM)
          type: cer
-         value: 9.25
+         value: 7.77
   - task: 
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
@@ -54,10 +54,14 @@ model-index:
          value: 8.93
 ---
 
-# XLS-R-1B-English
+# XLS-R-1B-ENGLISH
 
-This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - EN dataset.
+Fine-tuned [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on English using the [Common Voice 8](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0).
+When using this model, make sure that your speech input is sampled at 16kHz.
 
+This model has been fine-tuned thanks to the GPU credits generously given by the [OVHcloud](https://www.ovhcloud.com/en/public-cloud/ai-training/) :)
+
+The script used for training can be found here: https://github.com/jonatasgrosman/wav2vec2-sprint
 
 ## Evaluation Commands
 

mozilla-foundation_common_voice_8_0_en_test_eval_results.txt

@@ -1,2 +1,2 @@
-WER: 0.19585785349676496
-CER: 0.09254170290872085
+WER: 0.1731898429625776
+CER: 0.07770180904162725

mozilla-foundation_common_voice_8_0_en_test_eval_results_greedy.txt

@@ -1,2 +1,2 @@
-WER: 0.23601781708229022
-CER: 0.09938350966320014
+WER: 0.21057320284813213
+CER: 0.08449510053632464