Downloads · 30 days
28
21% of all-time downloads
pydiarize-Dataset-2_4
whitneyten/pydiarize-Dataset-2_4
pydiarize-Dataset-2_4 is a machine learning model from whitneyten. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers. The card lists the license as mit.
should probably proofread and complete it, then remove this comment. --
All-time downloads
132
Public
Parameters
1.5M
154 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.9 MB · 97%
At a glance
- Library
- transformers
- License
- mit
- Model type
- pyannet
- Access
- Public
- Created
- Apr 8, 2025
- Updated
- Apr 10, 2025
- SHA
- c6c444e3
Base models
Datasets
Model card
From the Hugging Face model README
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
speaker-segmentation-fine-tuned-datasetID-hugging_2_4
This model is a fine-tuned version of pyannote/speaker-diarization-3.1 on the speaker-segmentation dataset. It achieves the following results on the evaluation set:
- Loss: 0.3735
- Model Preparation Time: 0.0099
- Der: 0.1228
- False Alarm: 0.0205
- Missed Detection: 0.0096
- Confusion: 0.0927
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 43
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Model Preparation Time | Der | False Alarm | Missed Detection | Confusion |
|---|---|---|---|---|---|---|---|---|
| 0.4492 | 1.0 | 570 | 0.4525 | 0.0099 | 0.1515 | 0.0219 | 0.0094 | 0.1202 |
| 0.3875 | 2.0 | 1140 | 0.4229 | 0.0099 | 0.1403 | 0.0212 | 0.0098 | 0.1093 |
| 0.4014 | 3.0 | 1710 | 0.3889 | 0.0099 | 0.1324 | 0.0207 | 0.0102 | 0.1016 |
| 0.3656 | 4.0 | 2280 | 0.3899 | 0.0099 | 0.1305 | 0.0212 | 0.0094 | 0.1000 |
| 0.3232 | 5.0 | 2850 | 0.3804 | 0.0099 | 0.1283 | 0.0207 | 0.0096 | 0.0981 |
| 0.319 | 6.0 | 3420 | 0.3796 | 0.0099 | 0.1256 | 0.0204 | 0.0097 | 0.0956 |
| 0.3018 | 7.0 | 3990 | 0.3750 | 0.0099 | 0.1247 | 0.0202 | 0.0101 | 0.0945 |
| 0.2928 | 8.0 | 4560 | 0.3700 | 0.0099 | 0.1220 | 0.0203 | 0.0097 | 0.0920 |
| 0.3321 | 9.0 | 5130 | 0.3753 | 0.0099 | 0.1238 | 0.0204 | 0.0098 | 0.0936 |
| 0.2738 | 10.0 | 5700 | 0.3735 | 0.0099 | 0.1228 | 0.0205 | 0.0096 | 0.0927 |
Framework versions
- Transformers 4.50.3
- Pytorch 2.6.0+cu124
- Datasets 3.5.0
- Tokenizers 0.21.1
- Library
- transformers
- Type
- pyannet
- License
- mit
- Languages
- id
- Created
- Apr 8, 2025
- Updated
- Apr 10, 2025