Any-to-Any
ESPnet
PyTorch
English
audio
multimodal
speech-language-model
audio-understanding
audio-generation
text-to-audio
Instructions to use espnet/bagpiper-sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ESPnet
How to use espnet/bagpiper-sft with ESPnet:
unknown model type (must be text-to-speech or automatic-speech-recognition)
- Notebooks
- Google Colab
- Kaggle
| { | |
| "artifact": "espnet/bagpiper-sft", | |
| "format": "native ESPnet weight-only checkpoint", | |
| "weight_file": { | |
| "path": "model.pt", | |
| "bytes": 18188823609, | |
| "sha256": "50980756fad38bbefeb326ac0012e39f431ec5af8c0caaac8bd254f179f33746", | |
| "top_level_keys": ["module"], | |
| "tensor_count": 1382 | |
| }, | |
| "source": { | |
| "repo": "JinchuanTian/bagpiper_sft", | |
| "repo_type": "dataset", | |
| "revision": "b11d5a0c11ad488edd04e3734d4bdff764977f57", | |
| "path": "exp/opuslm_v2_stage2_pretrain_base/checkpoints/step_270000/global_step269985/mp_rank_00_model_states.pt", | |
| "bytes": 18188293839, | |
| "sha256": "e0d8fdd57c8cb8c938cd61ada43b20e469d9cea33ad8450e0971f80d4f9667b6" | |
| }, | |
| "validation": { | |
| "source_tensors_equal": 1381, | |
| "added_tensor": "vocab_weight", | |
| "strict_load": "pass", | |
| "espnet_revision": "1992821bfb6d68c6636d1b75340b8b2b591bc015", | |
| "transformers": "5.5.4", | |
| "pytorch": "2.12.1+cu129", | |
| "gpu": "NVIDIA H100 80GB HBM3" | |
| } | |
| } | |