Automatic Speech Recognition
Transformers
Safetensors
prosody_to_text
feature-extraction
prosody
speech-recognition
custom_code
Instructions to use Daporte/prosody2text-weights with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Daporte/prosody2text-weights with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Daporte/prosody2text-weights", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Daporte/prosody2text-weights", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download conformer/model_config.json from Daporte/prosody2text-weights: direct link, hf CLI and curl.
- Browser
- Download file 463 Bytes
-
https://huggingface.co/Daporte/prosody2text-weights/resolve/main/conformer/model_config.json
- Command line
-
hf download hf://Daporte/prosody2text-weights/conformer/model_config.json
-
curl -L -o model_config.json https://huggingface.co/Daporte/prosody2text-weights/resolve/main/conformer/model_config.json
463 Bytes
| { | |
| "input_dim": 2, | |
| "mel_dim": 12, | |
| "d_model": 256, | |
| "nhead": 4, | |
| "num_encoder_layers": 4, | |
| "num_decoder_layers": 4, | |
| "encoder_kernel_size": 7, | |
| "conv_kernel_size": 5, | |
| "gradient_checkpointing": true, | |
| "decoder_only": false, | |
| "attn_window": 256, | |
| "dropout": 0.1, | |
| "loss_type": "mse", | |
| "mel_bins": 12, | |
| "length_ratio": 0.5, | |
| "f0_key": "f0_interp", | |
| "intensity_key": "intensity", | |
| "extra_feature_keys": [], | |
| "model_type": "features_to_mel_conv" | |
| } |