|
--- |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: openai/whisper-large-v3 |
|
model-index: |
|
- name: whisper-large-v3-MH-fine-tuned |
|
results: [] |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# whisper-large-v3-MH-fine-tuned |
|
|
|
This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co./openai/whisper-large-v3) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1026 |
|
|
|
## 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: 10 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 50 |
|
- num_epochs: 100 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| No log | 1.0 | 1 | 1.6433 | |
|
| No log | 2.0 | 2 | 1.6256 | |
|
| No log | 3.0 | 3 | 1.5850 | |
|
| No log | 4.0 | 4 | 1.5268 | |
|
| No log | 5.0 | 5 | 1.4583 | |
|
| No log | 6.0 | 6 | 1.3911 | |
|
| No log | 7.0 | 7 | 1.3293 | |
|
| No log | 8.0 | 8 | 1.2727 | |
|
| No log | 9.0 | 9 | 1.2201 | |
|
| No log | 10.0 | 10 | 1.1695 | |
|
| No log | 11.0 | 11 | 1.1209 | |
|
| No log | 12.0 | 12 | 1.0779 | |
|
| No log | 13.0 | 13 | 1.0471 | |
|
| No log | 14.0 | 14 | 1.0264 | |
|
| No log | 15.0 | 15 | 1.0034 | |
|
| No log | 16.0 | 16 | 0.9841 | |
|
| No log | 17.0 | 17 | 0.9749 | |
|
| No log | 18.0 | 18 | 0.9693 | |
|
| No log | 19.0 | 19 | 0.9609 | |
|
| No log | 20.0 | 20 | 0.9441 | |
|
| No log | 21.0 | 21 | 0.9278 | |
|
| No log | 22.0 | 22 | 0.9189 | |
|
| No log | 23.0 | 23 | 0.9244 | |
|
| No log | 24.0 | 24 | 0.9232 | |
|
| 0.9846 | 25.0 | 25 | 0.9187 | |
|
| 0.9846 | 26.0 | 26 | 0.9295 | |
|
| 0.9846 | 27.0 | 27 | 0.9583 | |
|
| 0.9846 | 28.0 | 28 | 0.9774 | |
|
| 0.9846 | 29.0 | 29 | 0.9789 | |
|
| 0.9846 | 30.0 | 30 | 0.9960 | |
|
| 0.9846 | 31.0 | 31 | 1.0306 | |
|
| 0.9846 | 32.0 | 32 | 1.0483 | |
|
| 0.9846 | 33.0 | 33 | 1.0384 | |
|
| 0.9846 | 34.0 | 34 | 1.0458 | |
|
| 0.9846 | 35.0 | 35 | 1.0651 | |
|
| 0.9846 | 36.0 | 36 | 1.0418 | |
|
| 0.9846 | 37.0 | 37 | 1.0329 | |
|
| 0.9846 | 38.0 | 38 | 1.0425 | |
|
| 0.9846 | 39.0 | 39 | 1.0538 | |
|
| 0.9846 | 40.0 | 40 | 1.0397 | |
|
| 0.9846 | 41.0 | 41 | 1.0374 | |
|
| 0.9846 | 42.0 | 42 | 1.0477 | |
|
| 0.9846 | 43.0 | 43 | 1.0589 | |
|
| 0.9846 | 44.0 | 44 | 1.0609 | |
|
| 0.9846 | 45.0 | 45 | 1.0615 | |
|
| 0.9846 | 46.0 | 46 | 1.0700 | |
|
| 0.9846 | 47.0 | 47 | 1.0893 | |
|
| 0.9846 | 48.0 | 48 | 1.0948 | |
|
| 0.9846 | 49.0 | 49 | 1.0906 | |
|
| 0.2714 | 50.0 | 50 | 1.1002 | |
|
| 0.2714 | 51.0 | 51 | 1.1112 | |
|
| 0.2714 | 52.0 | 52 | 1.1162 | |
|
| 0.2714 | 53.0 | 53 | 1.1117 | |
|
| 0.2714 | 54.0 | 54 | 1.1243 | |
|
| 0.2714 | 55.0 | 55 | 1.1166 | |
|
| 0.2714 | 56.0 | 56 | 1.1230 | |
|
| 0.2714 | 57.0 | 57 | 1.1156 | |
|
| 0.2714 | 58.0 | 58 | 1.1162 | |
|
| 0.2714 | 59.0 | 59 | 1.1310 | |
|
| 0.2714 | 60.0 | 60 | 1.0921 | |
|
| 0.2714 | 61.0 | 61 | 1.1188 | |
|
| 0.2714 | 62.0 | 62 | 1.0336 | |
|
| 0.2714 | 63.0 | 63 | 0.9937 | |
|
| 0.2714 | 64.0 | 64 | 1.0263 | |
|
| 0.2714 | 65.0 | 65 | 1.0224 | |
|
| 0.2714 | 66.0 | 66 | 1.0067 | |
|
| 0.2714 | 67.0 | 67 | 1.0112 | |
|
| 0.2714 | 68.0 | 68 | 1.0143 | |
|
| 0.2714 | 69.0 | 69 | 1.0155 | |
|
| 0.2714 | 70.0 | 70 | 1.0211 | |
|
| 0.2714 | 71.0 | 71 | 1.0260 | |
|
| 0.2714 | 72.0 | 72 | 1.0292 | |
|
| 0.2714 | 73.0 | 73 | 1.0363 | |
|
| 0.2714 | 74.0 | 74 | 1.0443 | |
|
| 0.2554 | 75.0 | 75 | 1.0529 | |
|
| 0.2554 | 76.0 | 76 | 1.0624 | |
|
| 0.2554 | 77.0 | 77 | 1.0681 | |
|
| 0.2554 | 78.0 | 78 | 1.0688 | |
|
| 0.2554 | 79.0 | 79 | 1.0684 | |
|
| 0.2554 | 80.0 | 80 | 1.0690 | |
|
| 0.2554 | 81.0 | 81 | 1.0702 | |
|
| 0.2554 | 82.0 | 82 | 1.0719 | |
|
| 0.2554 | 83.0 | 83 | 1.0748 | |
|
| 0.2554 | 84.0 | 84 | 1.0789 | |
|
| 0.2554 | 85.0 | 85 | 1.0826 | |
|
| 0.2554 | 86.0 | 86 | 1.0848 | |
|
| 0.2554 | 87.0 | 87 | 1.0865 | |
|
| 0.2554 | 88.0 | 88 | 1.0876 | |
|
| 0.2554 | 89.0 | 89 | 1.0887 | |
|
| 0.2554 | 90.0 | 90 | 1.0898 | |
|
| 0.2554 | 91.0 | 91 | 1.0915 | |
|
| 0.2554 | 92.0 | 92 | 1.0934 | |
|
| 0.2554 | 93.0 | 93 | 1.0956 | |
|
| 0.2554 | 94.0 | 94 | 1.0978 | |
|
| 0.2554 | 95.0 | 95 | 1.0997 | |
|
| 0.2554 | 96.0 | 96 | 1.1010 | |
|
| 0.2554 | 97.0 | 97 | 1.1018 | |
|
| 0.2554 | 98.0 | 98 | 1.1023 | |
|
| 0.2554 | 99.0 | 99 | 1.1025 | |
|
| 0.2451 | 100.0 | 100 | 1.1026 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.11.1.dev0 |
|
- Transformers 4.40.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.19.1 |
