|
--- |
|
language: |
|
- en |
|
license: apache-2.0 |
|
base_model: openai/whisper-tiny |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- PolyAI/minds14 |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: Whisper Tiny English |
|
results: |
|
- task: |
|
name: Automatic Speech Recognition |
|
type: automatic-speech-recognition |
|
dataset: |
|
name: Minds 14 |
|
type: PolyAI/minds14 |
|
config: en-US |
|
split: train |
|
args: en-US |
|
metrics: |
|
- name: Wer |
|
type: wer |
|
value: 0.258610624635143 |
|
--- |
|
|
|
<!-- 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 Tiny English |
|
|
|
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Minds 14 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.4154 |
|
- Wer Ortho: 0.2659 |
|
- Wer: 0.2586 |
|
|
|
## 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: 1e-05 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 16 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: constant_with_warmup |
|
- lr_scheduler_warmup_steps: 20 |
|
- training_steps: 100 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:---------:|:------:| |
|
| 4.2901 | 0.33 | 5 | 4.2556 | 0.4220 | 0.2919 | |
|
| 4.3552 | 0.67 | 10 | 3.7784 | 0.4226 | 0.2931 | |
|
| 3.453 | 1.0 | 15 | 2.9546 | 0.4152 | 0.2907 | |
|
| 2.9147 | 1.33 | 20 | 2.4090 | 0.3988 | 0.2931 | |
|
| 2.3042 | 1.67 | 25 | 1.7869 | 0.3701 | 0.3001 | |
|
| 1.6056 | 2.0 | 30 | 1.1284 | 0.3494 | 0.3012 | |
|
| 0.988 | 2.33 | 35 | 0.6892 | 0.3860 | 0.3403 | |
|
| 0.6605 | 2.67 | 40 | 0.5611 | 0.3128 | 0.2849 | |
|
| 0.4645 | 3.0 | 45 | 0.4982 | 0.3091 | 0.2901 | |
|
| 0.4884 | 3.33 | 50 | 0.4640 | 0.2963 | 0.2855 | |
|
| 0.404 | 3.67 | 55 | 0.4453 | 0.2884 | 0.2814 | |
|
| 0.4745 | 4.0 | 60 | 0.4268 | 0.2762 | 0.2697 | |
|
| 0.303 | 4.33 | 65 | 0.4182 | 0.2829 | 0.2720 | |
|
| 0.2717 | 4.67 | 70 | 0.4119 | 0.2829 | 0.2750 | |
|
| 0.3464 | 5.0 | 75 | 0.4080 | 0.2860 | 0.2761 | |
|
| 0.2193 | 5.33 | 80 | 0.4054 | 0.2823 | 0.2750 | |
|
| 0.2138 | 5.67 | 85 | 0.4064 | 0.2762 | 0.2680 | |
|
| 0.1571 | 6.0 | 90 | 0.4102 | 0.2799 | 0.2715 | |
|
| 0.1398 | 6.33 | 95 | 0.4146 | 0.2768 | 0.2697 | |
|
| 0.1523 | 6.67 | 100 | 0.4154 | 0.2659 | 0.2586 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.31.0 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|
