Feature Extraction
Transformers
Safetensors
calmos
audio
speech
speech-quality-assessment
mos-prediction
speech-foundation-models
cal-mos
interspeech-2026
custom_code
Instructions to use alefiury/CALMOS-XLS-R-300m-BVCC with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use alefiury/CALMOS-XLS-R-300m-BVCC with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="alefiury/CALMOS-XLS-R-300m-BVCC", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("alefiury/CALMOS-XLS-R-300m-BVCC", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download config.json from alefiury/CALMOS-XLS-R-300m-BVCC: direct link, hf CLI and curl.
- Browser
- Download file 596 Bytes
-
https://huggingface.co/alefiury/CALMOS-XLS-R-300m-BVCC/resolve/main/config.json
- Command line
-
hf download hf://alefiury/CALMOS-XLS-R-300m-BVCC/config.json
-
curl -L -o config.json https://huggingface.co/alefiury/CALMOS-XLS-R-300m-BVCC/resolve/main/config.json
596 Bytes
| { | |
| "model_type": "calmos", | |
| "architectures": [ | |
| "CalMOS" | |
| ], | |
| "auto_map": { | |
| "AutoConfig": "configuration_calmos.CalMOSConfig", | |
| "AutoModel": "modeling_calmos.CalMOS" | |
| }, | |
| "backbone_name": "facebook/wav2vec2-xls-r-300m", | |
| "num_feature_layers": 25, | |
| "adapter_input_dim": 1024, | |
| "adapter_dim": 1024, | |
| "mlp_input_dim": 1024, | |
| "mlp_hidden_dim": 1024, | |
| "mlp_num_layers": 1, | |
| "mlp_output_size": 1, | |
| "mlp_dropout": 0.1, | |
| "target_sr": 16000, | |
| "mos_min": 1.0, | |
| "mos_max": 5.0, | |
| "layer_weight_strategy": "layer_adapter", | |
| "pooling_strategy": "mean", | |
| "freeze_backbone": true | |
| } | |