Instructions to use MU-NLPC/F0_Energy_joint_VQVAE_embeddings-preprocessor with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MU-NLPC/F0_Energy_joint_VQVAE_embeddings-preprocessor with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MU-NLPC/F0_Energy_joint_VQVAE_embeddings-preprocessor", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload config
Browse files- prosody_preprocessor.py +3 -1
prosody_preprocessor.py
CHANGED
|
@@ -66,7 +66,9 @@ class ProsodyPreprocessor(PreTrainedModel):
|
|
| 66 |
config_class = ProsodyConfig
|
| 67 |
|
| 68 |
def __init__(self, config: Optional[ProsodyConfig] = None):
|
| 69 |
-
|
|
|
|
|
|
|
| 70 |
self.speaker_stats: Dict[str, SpeakerStats] = {}
|
| 71 |
|
| 72 |
def extract_features(self, audio):
|
|
|
|
| 66 |
config_class = ProsodyConfig
|
| 67 |
|
| 68 |
def __init__(self, config: Optional[ProsodyConfig] = None):
|
| 69 |
+
config = config or ProsodyConfig()
|
| 70 |
+
super().__init__(config)
|
| 71 |
+
self.config = config
|
| 72 |
self.speaker_stats: Dict[str, SpeakerStats] = {}
|
| 73 |
|
| 74 |
def extract_features(self, audio):
|