update evaluation

README.md

@@ -22,16 +22,16 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 13.80
+         value: 11.01
        - name: Test CER
          type: cer
-         value: 3.41
+         value: 2.55
        - name: Test WER (+LM)
          type: wer
-         value: 9.31
+         value: 7.32
        - name: Test CER (+LM)
          type: cer
-         value: 2.69
+         value: 1.95
   - task: 
       name: Automatic Speech Recognition
       type: automatic-speech-recognition
@@ -56,7 +56,12 @@ model-index:
 
 # XLS-R-1B-POLISH
 
-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 - PL dataset.
+Fine-tuned [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on Polish 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_pl_test_eval_results.txt

@@ -1,2 +1,2 @@
-WER: 0.09312048650703154
-CER: 0.026951089299717294
+WER: 0.073265642250819
+CER: 0.01952608445291951

mozilla-foundation_common_voice_8_0_pl_test_eval_results_greedy.txt

@@ -1,2 +1,2 @@
-WER: 0.13804275035745958
-CER: 0.03418511584570111
+WER: 0.11018805089500643
+CER: 0.02559977314092752