|
--- |
|
library_name: transformers |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: whisper-small-es-ja |
|
results: [] |
|
datasets: |
|
- Marianoleiras/voxpopuli_es-ja |
|
language: |
|
- es |
|
- ja |
|
base_model: |
|
- openai/whisper-small |
|
--- |
|
|
|
<!-- 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-es-ja |
|
|
|
## Model Overview |
|
This model was developed as part of a workshop organized by Yasmin Moslem, focusing on **speech-to-text pipelines**. |
|
The workshop's primary goal was to enable accurate transcription and translation of spoken source languages into written target languages while learning about end-to-end and cascaded approaches in the process. |
|
|
|
This model represents an **end-to-end solution** for Spanish-to-Japanese speech-to-text (STT) tasks and is a fine-tuned version of OpenAI's Whisper-small, specifically trained on the **[Marianoleiras/voxpopuli_es-ja](https://huggingface.co/datasets/Marianoleiras/voxpopuli_es-ja)** dataset for Spanish-to-Japanese speech-to-text (STT) tasks. |
|
|
|
The model achieves performance metrics on the provided dataset: |
|
|
|
**Evaluation Set:** |
|
- Loss: **1.1724** |
|
- BLEU: **22.2850** |
|
|
|
**Test Set:** |
|
- BLEU: **20.8607** |
|
- ChrF++: **23.3571** |
|
- Comet: **77.6979** |
|
|
|
(Baseline evaluation on test set: BLEU 0.4793) |
|
|
|
## 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 |
|
- distributed_type: multi-GPU |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- training_steps: 3500 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Bleu | Validation Loss | |
|
|:-------------:|:------:|:----:|:-------:|:---------------:| |
|
| 1.5787 | 0.3962 | 250 | 11.6756 | 1.5196 | |
|
| 1.3535 | 0.7924 | 500 | 16.0514 | 1.3470 | |
|
| 1.0658 | 1.1886 | 750 | 17.7743 | 1.2533 | |
|
| 1.0303 | 1.5848 | 1000 | 19.1894 | 1.2046 | |
|
| 0.9893 | 1.9810 | 1250 | 20.1198 | 1.1591 | |
|
| 0.7569 | 2.3772 | 1500 | 21.0054 | 1.1546 | |
|
| 0.7571 | 2.7734 | 1750 | 21.6425 | 1.1378 | |
|
| 0.5557 | 3.1696 | 2000 | 21.7563 | 1.1500 | |
|
| 0.5612 | 3.5658 | 2250 | 21.1391 | 1.1395 | |
|
| 0.5581 | 3.9620 | 2500 | 22.0412 | 1.1343 | |
|
| 0.4144 | 4.3582 | 2750 | 22.2850 | 1.1724 | |
|
| 0.4114 | 4.7544 | 3000 | 22.1925 | 1.1681 | |
|
| 0.3005 | 5.1506 | 3250 | 21.4948 | 1.1947 | |
|
| 0.2945 | 5.5468 | 3500 | 22.1454 | 1.1921 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.47.1 |
|
- Pytorch 2.4.0+cu124 |
|
- Datasets 3.2.0 |
|
- Tokenizers 0.21.0 |
|
|
|
## Linked Models |
|
|
|
- **[Whisper-Small-es](https://huggingface.co/Marianoleiras/whisper-small-es)**: The ASR model of the cascaded approach built using this dataset. |
|
- **[NLLB-200-Distilled-es-ja](https://huggingface.co/Marianoleiras/nllb-200-distilled-es-ja)**: The MT model of the cascaded approach built using this dataset. |
|
|
|
# Model Card Contact |
|
|
|
Mariano González ([email protected]) |
