Instructions to use cuong4941/csm1b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cuong4941/csm1b-v2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-audio", model="cuong4941/csm1b-v2")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForTextToWaveform processor = AutoProcessor.from_pretrained("cuong4941/csm1b-v2") model = AutoModelForTextToWaveform.from_pretrained("cuong4941/csm1b-v2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Download preprocessor_config.json from cuong4941/csm1b-v2: direct link, hf CLI and curl.
- Browser
- Download file 271 Bytes
-
https://huggingface.co/cuong4941/csm1b-v2/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://cuong4941/csm1b-v2/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/cuong4941/csm1b-v2/resolve/main/preprocessor_config.json
271 Bytes
| { | |
| "chunk_length_s": null, | |
| "feature_extractor_type": "EncodecFeatureExtractor", | |
| "feature_size": 1, | |
| "overlap": null, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "processor_class": "CsmProcessor", | |
| "return_attention_mask": true, | |
| "sampling_rate": 24000 | |
| } | |