update evaluation

README.md

@@ -22,16 +22,16 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 16.02
+         value: 8.70
        - name: Test CER
          type: cer
-         value: 5.74
+         value: 2.55
        - name: Test WER (+LM)
          type: wer
-         value: 12.22
+         value: 6.04
        - name: Test CER (+LM)
          type: cer
-         value: 4.93
+         value: 1.98
   - task: 
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
@@ -56,8 +56,12 @@ model-index:
 
 # XLS-R-1B-PORTUGUESE
 
-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 - PT dataset.
+Fine-tuned [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on Portuguese 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_pt_test_eval_results.txt

@@ -1,2 +1,2 @@
-WER: 0.12223725755525484
-CER: 0.04932889298746021
+WER: 0.06040734186877624
+CER: 0.019840625488279754

mozilla-foundation_common_voice_8_0_pt_test_eval_results_greedy.txt

@@ -1,2 +1,2 @@
-WER: 0.160265084487006
-CER: 0.05745693181087068
+WER: 0.08703722979771694
+CER: 0.02556364717019862