Instructions to use OliBomby/CM3P with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use OliBomby/CM3P with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="OliBomby/CM3P", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("OliBomby/CM3P", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "auto_map": { | |
| "AutoProcessor": "processing_cm3p.CM3PProcessor" | |
| }, | |
| "default_kwargs": { | |
| "audio_kwargs": { | |
| "audio_length_per_tok": 8, | |
| "hop_length": 160, | |
| "max_source_positions": 1600, | |
| "pad_to_multiple_of": 256000, | |
| "padding": false, | |
| "sampling_rate": 16000, | |
| "truncation": false, | |
| "window_size": 400 | |
| }, | |
| "beatmap_kwargs": { | |
| "max_length": 2000, | |
| "padding": "longest", | |
| "truncation": "longest_first", | |
| "window_length_sec": 16.0, | |
| "window_stride_sec": 16.0 | |
| }, | |
| "common_kwargs": { | |
| "return_tensors": "pt" | |
| }, | |
| "metadata_kwargs": { | |
| "max_length": 128, | |
| "padding": "longest", | |
| "truncation": "longest_first" | |
| } | |
| }, | |
| "processor_class": "CM3PProcessor" | |
| } | |