|
--- |
|
language: |
|
- pl |
|
license: apache-2.0 |
|
tags: |
|
- mls |
|
- google/xtreme_s |
|
- generated_from_trainer |
|
datasets: |
|
- xtreme_s |
|
model-index: |
|
- name: xtreme_s_xlsr_mls_upd |
|
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. --> |
|
|
|
# xtreme_s_xlsr_mls_upd |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the GOOGLE/XTREME_S - MLS.PL dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 3.1489 |
|
- Wer: 1.0 |
|
- Cer: 1.0 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 32 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- total_train_batch_size: 64 |
|
- total_eval_batch_size: 16 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 1 |
|
- num_epochs: 3.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer | |
|
|:-------------:|:-----:|:----:|:---------------:|:---:|:---:| |
|
| 3.4678 | 0.59 | 20 | 3.4581 | 1.0 | 1.0 | |
|
| 3.1713 | 1.18 | 40 | 3.1816 | 1.0 | 1.0 | |
|
| 3.134 | 1.76 | 60 | 3.1538 | 1.0 | 1.0 | |
|
| 3.132 | 2.35 | 80 | 3.1411 | 1.0 | 1.0 | |
|
| 3.1295 | 2.94 | 100 | 3.1373 | 1.0 | 1.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.18.0.dev0 |
|
- Pytorch 1.10.2+cu113 |
|
- Datasets 1.18.4.dev0 |
|
- Tokenizers 0.11.6 |
|
|
