|
--- |
|
base_model: openai/whisper-medium |
|
language: |
|
- es |
|
library_name: peft |
|
license: apache-2.0 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: Whisper openai-whisper-medium-LoRA32-es_ecu911 |
|
results: [] |
|
--- |
|
|
|
<!-- 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 openai-whisper-medium-LoRA32-es_ecu911 |
|
|
|
This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the llamadas ecu9111 segmentos dmarquez dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5634 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 50 |
|
- num_epochs: 5 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 1.8188 | 1.0 | 53 | 1.7550 | |
|
| 1.7311 | 2.0 | 106 | 1.6299 | |
|
| 1.5613 | 3.0 | 159 | 1.5924 | |
|
| 1.5461 | 4.0 | 212 | 1.5718 | |
|
| 1.4195 | 5.0 | 265 | 1.5634 | |
|
|
|
|
|
### Framework versions |
|
|
|
- PEFT 0.13.2 |
|
- Transformers 4.45.2 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.1 |
|
- Tokenizers 0.20.1 |
