|
|
--- |
|
|
license: apache-2.0 |
|
|
base_model: openai/whisper-tiny |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
datasets: |
|
|
- PolyAI/minds14 |
|
|
metrics: |
|
|
- wer |
|
|
model-index: |
|
|
- name: whisper-small-dv |
|
|
results: |
|
|
- task: |
|
|
name: Automatic Speech Recognition |
|
|
type: automatic-speech-recognition |
|
|
dataset: |
|
|
name: PolyAI/minds14 |
|
|
type: PolyAI/minds14 |
|
|
config: en-US |
|
|
split: train |
|
|
args: en-US |
|
|
metrics: |
|
|
- name: Wer |
|
|
type: wer |
|
|
value: 34.454756380510446 |
|
|
--- |
|
|
|
|
|
<!-- 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-small-dv |
|
|
|
|
|
This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the PolyAI/minds14 dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.8668 |
|
|
- Wer Ortho: 34.2615 |
|
|
- Wer: 34.4548 |
|
|
|
|
|
## 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: 16 |
|
|
- 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: 50 |
|
|
- training_steps: 4000 |
|
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho | Wer | |
|
|
|:-------------:|:------:|:----:|:---------------:|:---------:|:-------:| |
|
|
| 0.0012 | 17.86 | 500 | 0.6821 | 33.2324 | 33.6427 | |
|
|
| 0.0002 | 35.71 | 1000 | 0.7362 | 34.0194 | 34.0487 | |
|
|
| 0.0001 | 53.57 | 1500 | 0.7689 | 33.9588 | 33.9907 | |
|
|
| 0.0001 | 71.43 | 2000 | 0.7934 | 34.5036 | 34.4548 | |
|
|
| 0.0 | 89.29 | 2500 | 0.8168 | 34.4431 | 34.3968 | |
|
|
| 0.0 | 107.14 | 3000 | 0.8352 | 34.5642 | 34.5708 | |
|
|
| 0.0 | 125.0 | 3500 | 0.8514 | 34.3220 | 34.5128 | |
|
|
| 0.0 | 142.86 | 4000 | 0.8668 | 34.2615 | 34.4548 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.35.2 |
|
|
- Pytorch 2.1.0+cu121 |
|
|
- Datasets 2.15.0 |
|
|
- Tokenizers 0.15.0 |
|
|
|
