Downloads · 30 days
11
4% of all-time downloads
speaker-segmentation-fine-tuned-callhome-jpn
anuragrawal/speaker-segmentation-fine-tuned-callhome-jpn
speaker-segmentation-fine-tuned-callhome-jpn is a machine learning model from anuragrawal. 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
256
Public
Parameters
1.5M
29.6 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors5.9 MB · 99%
At a glance
- Library
- transformers
- License
- mit
- Model type
- pyannet
- Access
- Public
- Created
- Apr 24, 2024
- Updated
- Apr 24, 2024
- SHA
- ab90f973
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-callhome-eng
This model is a fine-tuned version of pyannote/segmentation-3.0 on the diarizers-community/callhome dataset. It achieves the following results on the evaluation set:
- Loss: 0.4597
- Der: 0.1816
- False Alarm: 0.0595
- Missed Detection: 0.0708
- Confusion: 0.0513
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: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Der | False Alarm | Missed Detection | Confusion |
|---|---|---|---|---|---|---|---|
| 0.3871 | 1.0 | 362 | 0.4735 | 0.1913 | 0.0608 | 0.0744 | 0.0561 |
| 0.4079 | 2.0 | 724 | 0.4605 | 0.1850 | 0.0626 | 0.0700 | 0.0524 |
| 0.3871 | 3.0 | 1086 | 0.4603 | 0.1816 | 0.0581 | 0.0726 | 0.0509 |
| 0.3642 | 4.0 | 1448 | 0.4624 | 0.1817 | 0.0575 | 0.0723 | 0.0519 |
| 0.3421 | 5.0 | 1810 | 0.4597 | 0.1816 | 0.0595 | 0.0708 | 0.0513 |
Framework versions
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Library
- transformers
- Type
- pyannet
- License
- mit
- Languages
- eng
- Created
- Apr 24, 2024
- Updated
- Apr 24, 2024