Instructions to use 7ocho/WMAC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use 7ocho/WMAC with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="7ocho/WMAC")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("7ocho/WMAC") model = AutoModelForSpeechSeq2Seq.from_pretrained("7ocho/WMAC", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload preprocessor_config.json
Browse files
final_model/preprocessor_config.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"feature_extractor": {
|
| 3 |
+
"apply_spec_augment": true,
|
| 4 |
+
"chunk_length": 30,
|
| 5 |
+
"dither": 0.0,
|
| 6 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 7 |
+
"feature_size": 80,
|
| 8 |
+
"hop_length": 160,
|
| 9 |
+
"mask_feature_prob": 0.15,
|
| 10 |
+
"mask_time_prob": 0.15,
|
| 11 |
+
"n_fft": 400,
|
| 12 |
+
"n_samples": 480000,
|
| 13 |
+
"nb_max_frames": 3000,
|
| 14 |
+
"padding_side": "right",
|
| 15 |
+
"padding_value": 0.0,
|
| 16 |
+
"return_attention_mask": false,
|
| 17 |
+
"sampling_rate": 16000
|
| 18 |
+
},
|
| 19 |
+
"processor_class": "WhisperProcessor"
|
| 20 |
+
}
|