Transformers
TensorBoard
Safetensors
Indonesian
pyannet
speaker-diarization
speaker-segmentation
modality:audio
modality:text
format:parquet
Generated from Trainer
Instructions to use whitneyten/pydiarize-synthetic-data-updated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use whitneyten/pydiarize-synthetic-data-updated with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("whitneyten/pydiarize-synthetic-data-updated", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "SegmentationModel" | |
| ], | |
| "chunk_duration": 10.0, | |
| "max_speakers_per_chunk": 3, | |
| "max_speakers_per_frame": 2, | |
| "min_duration": null, | |
| "model_type": "pyannet", | |
| "sample_rate": 16000, | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.49.0", | |
| "warm_up": [ | |
| 0.0, | |
| 0.0 | |
| ], | |
| "weigh_by_cardinality": false | |
| } | |