Transformers
PyTorch
Safetensors
English
pyannet
speaker-diarization
speaker-segmentation
Generated from Trainer
Instructions to use JSWOOK/pyannote_3_fine_tuning with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JSWOOK/pyannote_3_fine_tuning with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("JSWOOK/pyannote_3_fine_tuning", dtype="auto") - Notebooks
- Google Colab
- Kaggle
Update config.yaml
Browse files- config.yaml +1 -1
config.yaml
CHANGED
|
@@ -4,7 +4,7 @@ chunk_duration: 10.0
|
|
| 4 |
max_speakers_per_chunk: 3
|
| 5 |
max_speakers_per_frame: 2
|
| 6 |
min_duration: null
|
| 7 |
-
model_type:
|
| 8 |
sample_rate: 16000
|
| 9 |
torch_dtype: float32
|
| 10 |
transformers_version: 4.44.2
|
|
|
|
| 4 |
max_speakers_per_chunk: 3
|
| 5 |
max_speakers_per_frame: 2
|
| 6 |
min_duration: null
|
| 7 |
+
model_type: pyannot.audio
|
| 8 |
sample_rate: 16000
|
| 9 |
torch_dtype: float32
|
| 10 |
transformers_version: 4.44.2
|