End of training
Browse files
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
base_model: pyannote/segmentation-3.0
|
| 4 |
+
tags:
|
| 5 |
+
- speaker-diarization
|
| 6 |
+
- speaker-segmentation
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- KMayanja/backup_and_callhome
|
| 10 |
+
model-index:
|
| 11 |
+
- name: speaker-segmentation-fine-tuned-merged-backup-uganda-callhome-eng
|
| 12 |
+
results: []
|
| 13 |
+
---
|
| 14 |
+
|
| 15 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
+
|
| 18 |
+
# speaker-segmentation-fine-tuned-merged-backup-uganda-callhome-eng
|
| 19 |
+
|
| 20 |
+
This model is a fine-tuned version of [pyannote/segmentation-3.0](https://huggingface.co/pyannote/segmentation-3.0) on the KMayanja/backup_and_callhome default dataset.
|
| 21 |
+
It achieves the following results on the evaluation set:
|
| 22 |
+
- Loss: 0.3085
|
| 23 |
+
- Der: 0.1123
|
| 24 |
+
- False Alarm: 0.0384
|
| 25 |
+
- Missed Detection: 0.0378
|
| 26 |
+
- Confusion: 0.0361
|
| 27 |
+
|
| 28 |
+
## Model description
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Intended uses & limitations
|
| 33 |
+
|
| 34 |
+
More information needed
|
| 35 |
+
|
| 36 |
+
## Training and evaluation data
|
| 37 |
+
|
| 38 |
+
More information needed
|
| 39 |
+
|
| 40 |
+
## Training procedure
|
| 41 |
+
|
| 42 |
+
### Training hyperparameters
|
| 43 |
+
|
| 44 |
+
The following hyperparameters were used during training:
|
| 45 |
+
- learning_rate: 0.001
|
| 46 |
+
- train_batch_size: 32
|
| 47 |
+
- eval_batch_size: 32
|
| 48 |
+
- seed: 42
|
| 49 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 50 |
+
- lr_scheduler_type: cosine
|
| 51 |
+
- num_epochs: 5.0
|
| 52 |
+
|
| 53 |
+
### Training results
|
| 54 |
+
|
| 55 |
+
| Training Loss | Epoch | Step | Validation Loss | Der | False Alarm | Missed Detection | Confusion |
|
| 56 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:-----------:|:----------------:|:---------:|
|
| 57 |
+
| 0.3367 | 1.0 | 605 | 0.3336 | 0.1237 | 0.0481 | 0.0369 | 0.0387 |
|
| 58 |
+
| 0.3267 | 2.0 | 1210 | 0.3148 | 0.1155 | 0.0416 | 0.0353 | 0.0386 |
|
| 59 |
+
| 0.302 | 3.0 | 1815 | 0.3119 | 0.1124 | 0.0394 | 0.0379 | 0.0351 |
|
| 60 |
+
| 0.29 | 4.0 | 2420 | 0.3088 | 0.1125 | 0.0393 | 0.0370 | 0.0361 |
|
| 61 |
+
| 0.288 | 5.0 | 3025 | 0.3085 | 0.1123 | 0.0384 | 0.0378 | 0.0361 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.42.4
|
| 67 |
+
- Pytorch 2.3.1+cu121
|
| 68 |
+
- Datasets 2.20.0
|
| 69 |
+
- Tokenizers 0.19.1
|