|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
datasets: |
|
|
- StofEzz/dataset_c_voice0.2 |
|
|
metrics: |
|
|
- wer |
|
|
base_model: |
|
|
- openai/whisper-tiny |
|
|
--- |
|
|
|
|
|
## Training Details |
|
|
|
|
|
#### Training Hyperparameters |
|
|
```yaml |
|
|
defaults: |
|
|
- _self_ |
|
|
dataset: |
|
|
name: "StofEzz/dataset_c_voice0.2" |
|
|
audio_sampling_rate: 16000 |
|
|
num_proc_preprocessing: 4 |
|
|
num_proc_dataset_map: 2 |
|
|
train: 80 |
|
|
test: 20 |
|
|
|
|
|
model: |
|
|
name: "openai/whisper-tiny" |
|
|
language: "french" |
|
|
task: "transcribe" |
|
|
|
|
|
text_preprocessing: |
|
|
chars_to_ignore_regex: "[\\,\\?\\.\\!\\-\\;\\:\\ğ\\ź\\…\\ø\\ắ\\î\\´\\ŏ\\ę\\ź\\&\\'\\v\\ï\\ū\\ė\\ō\\ń\\ø\\…\\σ\\$\\ă\\ß\\ž\\ṯ\\ý\\ℵ\\đ\\ł\\ś\\ň\\ạ\\=\\_\\»\\ċ\\の\\\"\\ぬ\\ễ\\ż\\ć\\ů\\ʿ\\ș\\ı\\ñ\\(\\ò\\ř\\ä\\–\\ş\\«\\š\\ጠ\\°\\ℤ\\~\\\"\\ī\\ț\\č\\ả\\—\\)\\ā\\/\\½\"]" |
|
|
|
|
|
training_args: |
|
|
_target_: transformers.Seq2SeqTrainingArguments |
|
|
output_dir: ./models |
|
|
per_device_train_batch_size: 16 |
|
|
gradient_accumulation_steps: 1 |
|
|
learning_rate: 1e-5 |
|
|
warmup_steps: 500 |
|
|
max_steps: 6250 |
|
|
gradient_checkpointing: true |
|
|
fp16: true |
|
|
evaluation_strategy: "steps" |
|
|
per_device_eval_batch_size: 8 |
|
|
predict_with_generate: true |
|
|
generation_max_length: 225 |
|
|
save_steps: 2000 |
|
|
eval_steps: 100 |
|
|
logging_steps: 25 |
|
|
load_best_model_at_end: true |
|
|
metric_for_best_model: "wer" |
|
|
greater_is_better: false |
|
|
push_to_hub: false |
|
|
``` |
|
|
|
|
|
#### Metrics |
|
|
|
|
|
WER: 0.46 |
|
|
|
|
|
<!-- These are the evaluation metrics being used, ideally with a description of why. --> |
