Instructions to use dg845/univnet-dev with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dg845/univnet-dev with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="dg845/univnet-dev")# pip install -U transformers accelerate # Load model directly from transformers import AutoFeatureExtractor, AutoModel extractor = AutoFeatureExtractor.from_pretrained("dg845/univnet-dev") model = AutoModel.from_pretrained("dg845/univnet-dev", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Delete preprocessor_config.json
Browse filesRemove old feature extractor config (feature extractor has been updated).
- preprocessor_config.json +0 -26
preprocessor_config.json
DELETED
|
@@ -1,26 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"center": false,
|
| 3 |
-
"compression_clip_val": 1e-05,
|
| 4 |
-
"compression_factor": 1.0,
|
| 5 |
-
"do_normalize": false,
|
| 6 |
-
"feature_extractor_type": "UnivNetFeatureExtractor",
|
| 7 |
-
"feature_size": 1,
|
| 8 |
-
"filter_length": 1024,
|
| 9 |
-
"fmax": 12000.0,
|
| 10 |
-
"fmin": 0.0,
|
| 11 |
-
"frame_signal_scale": 1.0,
|
| 12 |
-
"hop_length": 256,
|
| 13 |
-
"max_length_s": 10,
|
| 14 |
-
"mel_floor": 1e-09,
|
| 15 |
-
"normalize_max": 2.3143386840820312,
|
| 16 |
-
"normalize_min": -11.512925148010254,
|
| 17 |
-
"num_max_samples": 240000,
|
| 18 |
-
"num_mel_bins": 100,
|
| 19 |
-
"padding_side": "right",
|
| 20 |
-
"padding_value": 0.0,
|
| 21 |
-
"reduction_factor": 2,
|
| 22 |
-
"return_attention_mask": true,
|
| 23 |
-
"sampling_rate": 24000,
|
| 24 |
-
"win_function": "hann_window",
|
| 25 |
-
"win_length": 1024
|
| 26 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|