Feature Extraction
Transformers
Safetensors
English
AuriStream.AuriStream
audio
speech
autoregressive
custom_code
Instructions to use TuKoResearch/AuriStream1B_1Pred_librilight_500k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TuKoResearch/AuriStream1B_1Pred_librilight_500k with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="TuKoResearch/AuriStream1B_1Pred_librilight_500k", trust_remote_code=True)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TuKoResearch/AuriStream1B_1Pred_librilight_500k", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "_name_or_path": "TuKoResearch/AuriStream1B_1Pred_librilight_500k", | |
| "architectures": ["AuriStream"], | |
| "model_type": "AuriStream.AuriStream", | |
| "auto_map": { | |
| "AutoConfig": "configuration_auristream.AuriStreamConfig", | |
| "AutoModel": "modeling_auristream.AuriStream", | |
| "AutoModelForCausalLM": "modeling_auristream.AuriStream" | |
| }, | |
| "vocab_size": 8192, | |
| "n_embd": 1280, | |
| "n_layer": 48, | |
| "n_head": 16, | |
| "dropout": 0.0, | |
| "bias": false, | |
| "use_rope": false, | |
| "n_pred_steps": 1, | |
| "seq_len": 4096 | |
| } | |