Automatic Speech Recognition
MLX
PyTorch
TensorFlow
Safetensors
English
wav2vec2
audio
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use HashNuke/wav2vec2-base-960h-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use HashNuke/wav2vec2-base-960h-mlx with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir wav2vec2-base-960h-mlx HashNuke/wav2vec2-base-960h-mlx
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
Commit ·
407ffc2
1
Parent(s): 829b55c
Update README.md
Browse files
README.md
CHANGED
|
@@ -100,7 +100,7 @@ def map_to_pred(batch):
|
|
| 100 |
batch["transcription"] = transcription
|
| 101 |
return batch
|
| 102 |
|
| 103 |
-
result = librispeech_eval.map(map_to_pred, batched=True, batch_size=
|
| 104 |
|
| 105 |
print("WER:", wer(result["text"], result["transcription"]))
|
| 106 |
```
|
|
|
|
| 100 |
batch["transcription"] = transcription
|
| 101 |
return batch
|
| 102 |
|
| 103 |
+
result = librispeech_eval.map(map_to_pred, batched=True, batch_size=1, remove_columns=["speech"])
|
| 104 |
|
| 105 |
print("WER:", wer(result["text"], result["transcription"]))
|
| 106 |
```
|