speechbrain
/

asr-wav2vec2-commonvoice-en

Automatic Speech Recognition speechbrain PyTorch

English wav2vec2 CTC Transformer

Model card Files Files and versions Community

Titouan commited on Jun 3, 2021

Commit

e9fe597

•

1 Parent(s): 08e3512

output

Files changed (2) hide show

README.md +1 -1
hyperparams.yaml +1 -1

README.md CHANGED Viewed

@@ -57,7 +57,7 @@ Please notice that we encourage you to read our tutorials and learn more about
 ```python
 from speechbrain.pretrained import EncoderDecoderASR
-asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-wav2vec2-commonvoice-fr", savedir="pretrained_models/asr-wav2vec2-commonvoice-en")
 asr_model.transcribe_file("example.wav")
 ```

 ```python
 from speechbrain.pretrained import EncoderDecoderASR
+asr_model = EncoderDecoderASR.from_hparams(source="speechbrain/asr-wav2vec2-commonvoice-en", savedir="pretrained_models/asr-wav2vec2-commonvoice-en")
 asr_model.transcribe_file("example.wav")
 ```

hyperparams.yaml CHANGED Viewed

@@ -19,7 +19,7 @@ emb_size: 128
 dec_neurons: 1024
 # Outputs
-output_neurons: 500  # BPE size, index(blank/eos/bos) = 0
 # Decoding parameters
 # Be sure that the bos and eos index match with the BPEs ones

 dec_neurons: 1024
 # Outputs
+output_neurons: 1000  # BPE size, index(blank/eos/bos) = 0
 # Decoding parameters
 # Be sure that the bos and eos index match with the BPEs ones