Instructions to use descript/dac_16khz with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use descript/dac_16khz with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="descript/dac_16khz")# Load model directly from transformers import AutoFeatureExtractor, AutoModel extractor = AutoFeatureExtractor.from_pretrained("descript/dac_16khz") model = AutoModel.from_pretrained("descript/dac_16khz", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Upload model
Browse files- config.json +1 -2
config.json
CHANGED
|
@@ -14,10 +14,9 @@
|
|
| 14 |
"encoder_hidden_size": 64,
|
| 15 |
"hidden_size": 1024,
|
| 16 |
"hop_length": 512,
|
| 17 |
-
"latent_dim": null,
|
| 18 |
"model_type": "dac",
|
| 19 |
"n_codebooks": 12,
|
| 20 |
-
"quantizer_dropout":
|
| 21 |
"torch_dtype": "float32",
|
| 22 |
"transformers_version": "4.42.0.dev0",
|
| 23 |
"upsampling_ratios": [
|
|
|
|
| 14 |
"encoder_hidden_size": 64,
|
| 15 |
"hidden_size": 1024,
|
| 16 |
"hop_length": 512,
|
|
|
|
| 17 |
"model_type": "dac",
|
| 18 |
"n_codebooks": 12,
|
| 19 |
+
"quantizer_dropout": 0.0,
|
| 20 |
"torch_dtype": "float32",
|
| 21 |
"transformers_version": "4.42.0.dev0",
|
| 22 |
"upsampling_ratios": [
|