|
--- |
|
base_model: openai/whisper-small |
|
datasets: |
|
- mozilla-foundation/common_voice_11_0 |
|
language: |
|
- yo |
|
license: apache-2.0 |
|
metrics: |
|
- wer |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Whisper Small Yo - Bola Ologundudu |
|
results: |
|
- task: |
|
type: automatic-speech-recognition |
|
name: Automatic Speech Recognition |
|
dataset: |
|
name: Common Voice 11.0 |
|
type: mozilla-foundation/common_voice_11_0 |
|
config: yo |
|
split: None |
|
args: 'config: yo, split: test' |
|
metrics: |
|
- type: wer |
|
value: 70.61345018098686 |
|
name: Wer |
|
--- |
|
|
|
<!-- 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 Yoruba - Bola Ologundudu |
|
|
|
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.2225 |
|
- Wer: 70.6135 |
|
|
|
## Model description |
|
|
|
>>> from transformers import pipeline |
|
>>> import torch |
|
|
|
>>> modelName="ajibs75/whisper-small-yoruba" |
|
>>> device = 0 if torch.cuda.is_available() else "cpu" |
|
>>> pipe = pipeline(task="automatic-speech-recognition",model=modelName,chunk_length_s=30,device=device,) |
|
>>> pipe.model.config.forced_decoder_ids = pipe.tokenizer.get_decoder_prompt_ids(language="yo", task="transcribe") |
|
|
|
>>> audio = "sample.mp3" |
|
>>> text = pipe(audio) |
|
>>> transacribed_audio = text["text"] |
|
>>> print(transacribed_audio) |
|
|
|
|
|
## 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: 8 |
|
- 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 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-------:|:----:|:---------------:|:-------:| |
|
| 0.066 | 7.6923 | 1000 | 0.8962 | 74.0141 | |
|
| 0.004 | 15.3846 | 2000 | 1.1411 | 71.6613 | |
|
| 0.0004 | 23.0769 | 3000 | 1.1959 | 70.6516 | |
|
| 0.0003 | 30.7692 | 4000 | 1.2225 | 70.6135 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.42.4 |
|
- Pytorch 2.1.0+cu118 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
