|
--- |
|
language: |
|
- ru |
|
license: apache-2.0 |
|
library_name: peft |
|
tags: |
|
- generated_from_trainer |
|
base_model: openai/whisper-small |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: 'Whisper Small Ru ORD 0.7 PEFT LoRA - Mizoru ' |
|
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. --> |
|
|
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/mizoru/ORD/runs/jbal64q5) |
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/mizoru/ORD/runs/jbal64q5) |
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/mizoru/ORD/runs/jbal64q5) |
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/mizoru/ORD/runs/o1p7x7u1) |
|
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/mizoru/ORD/runs/o1p7x7u1) |
|
# Whisper Small Ru ORD 0.7 PEFT LoRA - Mizoru |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the ORD_0.7 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.4241 |
|
- Wer: 74.5818 |
|
- Cer: 38.6379 |
|
- Clean Wer: 60.9733 |
|
- Clean Cer: 30.4133 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 50 |
|
- training_steps: 2000 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | Clean Wer | Clean Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:-------:|:---------:|:---------:| |
|
| 1.3116 | 1.0 | 196 | 1.2595 | 75.2427 | 37.5133 | 59.8253 | 30.3495 | |
|
| 1.1944 | 2.0 | 392 | 1.2362 | 75.3239 | 38.0798 | 61.7830 | 31.1456 | |
|
| 1.137 | 3.0 | 588 | 1.2391 | 76.7957 | 39.3375 | 62.8324 | 31.6562 | |
|
| 1.0293 | 4.0 | 784 | 1.2472 | 74.9783 | 38.2671 | 58.8861 | 30.9703 | |
|
| 0.9835 | 5.0 | 980 | 1.2720 | 72.7755 | 37.0461 | 58.5421 | 28.9427 | |
|
| 0.92 | 6.0 | 1176 | 1.2871 | 72.1532 | 37.6018 | 62.6024 | 30.6224 | |
|
| 0.849 | 7.0 | 1372 | 1.3214 | 72.6281 | 37.3213 | 58.2328 | 29.4501 | |
|
| 0.7708 | 8.0 | 1568 | 1.3527 | 72.0761 | 37.4703 | 60.3471 | 29.9594 | |
|
| 0.7397 | 9.0 | 1764 | 1.3923 | 74.3780 | 38.5124 | 60.8670 | 30.1533 | |
|
| 0.6614 | 10.0 | 1960 | 1.4241 | 74.5818 | 38.6379 | 60.9733 | 30.4133 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.10.1.dev0 |
|
- Transformers 4.41.0.dev0 |
|
- Pytorch 2.1.2 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.19.1 |
