|
--- |
|
language: |
|
- ml |
|
license: apache-2.0 |
|
tags: |
|
- whisper-event |
|
- generated_from_trainer |
|
datasets: |
|
- thennal/imasc |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: Whisper Small Ml - IMaSC |
|
results: |
|
- task: |
|
name: Automatic Speech Recognition |
|
type: automatic-speech-recognition |
|
dataset: |
|
name: ICFOSS Malayalam Speech Corpus |
|
type: thennal/imasc |
|
config: ml |
|
split: test |
|
args: ml |
|
metrics: |
|
- name: Wer |
|
type: wer |
|
value: 10.945945945945947 |
|
--- |
|
|
|
# Whisper Small Ml - IMaSC |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the [ICFOSS Malayalam Speech Corpus](https://huggingface.co/datasets/thennal/IMaSC) dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.0244 |
|
- Wer: 10.9459 |
|
- Cer: 1.7890 |
|
|
|
## 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: 64 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- training_steps: 4000 |
|
- mixed_precision_training: Native AMP |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.26.0.dev0 |
|
- Pytorch 1.13.0+cu117 |
|
- Datasets 2.7.1.dev0 |
|
- Tokenizers 0.13.2 |
|
|
