nithinholla
/

wav2vec2-large-xlsr-53-dutch

Automatic Speech Recognition Transformers PyTorch

Dutch wav2vec2 audio speech xlsr-fine-tuning-week Eval Results Inference Endpoints

Model card Files Files and versions Community

nithinholla commited on Mar 28, 2021

Commit

ab884ee

•

1 Parent(s): 260efc1

Updated model

Files changed (3) hide show

README.md +2 -2
config.json +1 -1
pytorch_model.bin +2 -2

README.md CHANGED Viewed

@@ -23,7 +23,7 @@ model-index:
     metrics:
        - name: Test WER
          type: wer
-         value: 21.72
 ---
 # Wav2Vec2-Large-XLSR-53-Dutch
@@ -116,7 +116,7 @@ result = test_dataset.map(evaluate, batched=True, batch_size=8)
 print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
 ```
-**Test Result**: 21.72 %
 ## Training

     metrics:
        - name: Test WER
          type: wer
+         value: 21.59
 ---
 # Wav2Vec2-Large-XLSR-53-Dutch
 print("WER: {:2f}".format(100 * wer.compute(predictions=result["pred_strings"], references=result["sentence"])))
 ```
+**Test Result**: 21.59 %
 ## Training

config.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "/workspace/models/nl_third/checkpoint-13000",
   "activation_dropout": 0.1,
   "apply_spec_augment": true,
   "architectures": [

 {
+  "_name_or_path": "/facebook/wav2vec2-large-xlsr-53",
   "activation_dropout": 0.1,
   "apply_spec_augment": true,
   "architectures": [

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d66e36e390922ffe5ab48bcd36d637e94d3058955e987c62e41a04a276d368e
-size 1262106007

 version https://git-lfs.github.com/spec/v1
+oid sha256:25d5293b22070fae58258f532c88cc28bb840399b2a26b013ac7667c1eed076e
+size 1262106008