patrickvonplaten
/

wav2vec2-xlsr-53-es-kenlm

Automatic Speech Recognition

xlsr-fine-tuning-week

Inference Endpoints

Model card Files Files and versions Community

patrickvonplaten commited on Dec 8, 2021

Commit

cc167e7

·

1 Parent(s): dae4c10

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -33,7 +33,7 @@ from transformers import AutoModelForCTC, AutoProcessor
 import torchaudio.functional as F
-model_id = "patrickvonplaten/wav2vec2-large-xlsr-53-spanish-with-lm"
 sample = next(iter(load_dataset("common_voice", "es", split="test", streaming=True)))
 resampled_audio = F.resample(torch.tensor(sample["audio"]["array"]), 48_000, 16_000).numpy()
@@ -61,7 +61,7 @@ The results can be reproduced by running *from this model repository*:
 | Model | WER | CER |
 | ------------- | ------------- | ------------- |
-| patrickvonplaten/wav2vec2-large-xlsr-53-spanish-with-lm | **8.44%** | **2.93%** |
 | jonatasgrosman/wav2vec2-large-xlsr-53-spanish | **10.20%** | **3.24%** |
 ```

 import torchaudio.functional as F
+model_id = "patrickvonplaten/wav2vec2-xlsr-53-es-kenlm"
 sample = next(iter(load_dataset("common_voice", "es", split="test", streaming=True)))
 resampled_audio = F.resample(torch.tensor(sample["audio"]["array"]), 48_000, 16_000).numpy()
 | Model | WER | CER |
 | ------------- | ------------- | ------------- |
+| patrickvonplaten/wav2vec2-xlsr-53-es-kenlm | **8.44%** | **2.93%** |
 | jonatasgrosman/wav2vec2-large-xlsr-53-spanish | **10.20%** | **3.24%** |
 ```