Wav2Vec2 model is updated.

README.md

@@ -24,10 +24,10 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 9.85
+         value: 7.985
        - name: Test CER
          type: cer
-         value: 2.36
+         value: 2.014
   - task:
       name: Speech Recognition
       type: automatic-speech-recognition
@@ -38,15 +38,16 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 20.64
+         value: 19.912
        - name: Test CER
          type: cer
-         value: 5.55
+         value: 5.904
 ---
 
 # Wav2Vec2-Large-Ru-Golos
 
-Fine-tuned [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on Russian using the [Sberdevices Golos](https://huggingface.co/datasets/SberDevices/Golos).
+The Wav2Vec2 model is based on [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53), fine-tuned in Russian using [Sberdevices Golos](https://huggingface.co/datasets/SberDevices/Golos) with audio augmentations like as pitch shift, acceleration/deceleration of sound, reverberation etc.
+
 When using this model, make sure that your speech input is sampled at 16kHz.
 
 ## Citation
@@ -61,4 +62,4 @@ If you want to cite this model you can use this:
   howpublished={\url{https://huggingface.co/bond005/wav2vec2-large-ru-golos}},
   year={2022}
 }
-```
+```

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95f1f19d457308fe13c16958c4c7edf43472eaf4f48ed97436348e299049ee0c
-size 1262075377
+oid sha256:8175e932bb5a549412f033265b8f6382a2df4ecb6ef5647a03dd78a9a2d777bd
+size 1262044529