|
--- |
|
license: apache-2.0 |
|
base_model: facebook/wav2vec2-xls-r-300m |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: 1-epochs5-char-based-freeze_cnn-dropout0.1 |
|
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. --> |
|
|
|
# 1-epochs5-char-based-freeze_cnn-dropout0.1 |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1245 |
|
- Wer: 0.0865 |
|
|
|
## 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: 2e-05 |
|
- train_batch_size: 10 |
|
- eval_batch_size: 2 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 4 |
|
- total_train_batch_size: 40 |
|
- total_eval_batch_size: 8 |
|
- optimizer: Adam with betas=(0.9,0.98) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.1 |
|
- num_epochs: 5 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:| |
|
| 2.8545 | 0.37 | 2500 | 2.8872 | 1.0 | |
|
| 0.7012 | 0.74 | 5000 | 0.3473 | 0.2840 | |
|
| 0.46 | 1.11 | 7500 | 0.2032 | 0.1510 | |
|
| 0.3848 | 1.48 | 10000 | 0.1668 | 0.1194 | |
|
| 0.3535 | 1.85 | 12500 | 0.1518 | 0.1086 | |
|
| 0.3667 | 2.22 | 15000 | 0.1442 | 0.1019 | |
|
| 0.3058 | 2.59 | 17500 | 0.1381 | 0.0961 | |
|
| 0.3026 | 2.96 | 20000 | 0.1327 | 0.0924 | |
|
| 0.2891 | 3.33 | 22500 | 0.1326 | 0.0917 | |
|
| 0.294 | 3.7 | 25000 | 0.1278 | 0.0894 | |
|
| 0.2846 | 4.07 | 27500 | 0.1257 | 0.0885 | |
|
| 0.259 | 4.44 | 30000 | 0.1244 | 0.0874 | |
|
| 0.2348 | 4.81 | 32500 | 0.1245 | 0.0865 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.34.0 |
|
- Pytorch 2.0.1 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.14.1 |
|
|
