Instructions to use sweetcocoa/pop2piano with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use sweetcocoa/pop2piano with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="sweetcocoa/pop2piano")# Load model directly from transformers import AutoModelForSpeechSeq2Seq model = AutoModelForSpeechSeq2Seq.from_pretrained("sweetcocoa/pop2piano", dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "feature_extractor_type": "Pop2PianoFeatureExtractor", | |
| "start_token_id": 0, | |
| "target_length": 256, | |
| "input_length": 1024, | |
| "num_bars": 2, | |
| "sampling_rate": 22050, | |
| "mel_is_conditioned": true, | |
| "padding_value": 0, | |
| "eos_token_id": 1, | |
| "default_velocity": 77, | |
| "window_size":4096, | |
| "hop_length":1024, | |
| "min_frequency":10.0, | |
| "feature_size":512 | |
| } |