|
--- |
|
language: |
|
- ga-IE |
|
license: apache-2.0 |
|
tags: |
|
- automatic-speech-recognition |
|
- mozilla-foundation/common_voice_7_0 |
|
- generated_from_trainer |
|
datasets: |
|
- common_voice |
|
model-index: |
|
- name: '' |
|
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. --> |
|
|
|
# |
|
|
|
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-1b](https://huggingface.co/facebook/wav2vec2-xls-r-1b) on the MOZILLA-FOUNDATION/COMMON_VOICE_7_0 - GA-IE dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: nan |
|
- Wer: 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: 5e-05 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 4 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 100.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:-----:|:---------------:|:---:| |
|
| 3.0395 | 1.94 | 500 | 3.0831 | 1.0 | |
|
| 3.0126 | 3.87 | 1000 | 2.9935 | 1.0 | |
|
| 2.9259 | 5.81 | 1500 | 2.9915 | 1.0 | |
|
| 2.9109 | 7.75 | 2000 | 2.9006 | 1.0 | |
|
| 2.8934 | 9.69 | 2500 | 2.9266 | 1.0 | |
|
| 2.9014 | 11.63 | 3000 | 2.8970 | 1.0 | |
|
| 2.8932 | 13.56 | 3500 | 2.8874 | 1.0 | |
|
| 0.0 | 15.5 | 4000 | nan | 1.0 | |
|
| 0.0 | 17.44 | 4500 | nan | 1.0 | |
|
| 0.0 | 19.38 | 5000 | nan | 1.0 | |
|
| 0.0 | 21.32 | 5500 | nan | 1.0 | |
|
| 0.0 | 23.26 | 6000 | nan | 1.0 | |
|
| 0.0 | 25.19 | 6500 | nan | 1.0 | |
|
| 0.0 | 27.13 | 7000 | nan | 1.0 | |
|
| 0.0 | 29.07 | 7500 | nan | 1.0 | |
|
| 0.0 | 31.01 | 8000 | nan | 1.0 | |
|
| 0.0 | 32.94 | 8500 | nan | 1.0 | |
|
| 0.0 | 34.88 | 9000 | nan | 1.0 | |
|
| 0.0 | 36.82 | 9500 | nan | 1.0 | |
|
| 0.0 | 38.76 | 10000 | nan | 1.0 | |
|
| 0.0 | 40.7 | 10500 | nan | 1.0 | |
|
| 0.0 | 42.63 | 11000 | nan | 1.0 | |
|
| 0.0 | 44.57 | 11500 | nan | 1.0 | |
|
| 0.0 | 46.51 | 12000 | nan | 1.0 | |
|
| 0.0 | 48.45 | 12500 | nan | 1.0 | |
|
| 0.0 | 50.39 | 13000 | nan | 1.0 | |
|
| 0.0 | 52.32 | 13500 | nan | 1.0 | |
|
| 0.0 | 54.26 | 14000 | nan | 1.0 | |
|
| 0.0 | 56.2 | 14500 | nan | 1.0 | |
|
| 0.0 | 58.14 | 15000 | nan | 1.0 | |
|
| 0.0 | 60.08 | 15500 | nan | 1.0 | |
|
| 0.0 | 62.02 | 16000 | nan | 1.0 | |
|
| 0.0 | 63.95 | 16500 | nan | 1.0 | |
|
| 0.0 | 65.89 | 17000 | nan | 1.0 | |
|
| 0.0 | 67.83 | 17500 | nan | 1.0 | |
|
| 0.0 | 69.77 | 18000 | nan | 1.0 | |
|
| 0.0 | 71.7 | 18500 | nan | 1.0 | |
|
| 0.0 | 73.64 | 19000 | nan | 1.0 | |
|
| 0.0 | 75.58 | 19500 | nan | 1.0 | |
|
| 0.0 | 77.52 | 20000 | nan | 1.0 | |
|
| 0.0 | 79.46 | 20500 | nan | 1.0 | |
|
| 0.0 | 81.39 | 21000 | nan | 1.0 | |
|
| 0.0 | 83.33 | 21500 | nan | 1.0 | |
|
| 0.0 | 85.27 | 22000 | nan | 1.0 | |
|
| 0.0 | 87.21 | 22500 | nan | 1.0 | |
|
| 0.0 | 89.15 | 23000 | nan | 1.0 | |
|
| 0.0 | 91.09 | 23500 | nan | 1.0 | |
|
| 0.0 | 93.02 | 24000 | nan | 1.0 | |
|
| 0.0 | 94.96 | 24500 | nan | 1.0 | |
|
| 0.0 | 96.9 | 25000 | nan | 1.0 | |
|
| 0.0 | 98.83 | 25500 | nan | 1.0 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.16.0.dev0 |
|
- Pytorch 1.10.1+cu102 |
|
- Datasets 1.17.1.dev0 |
|
- Tokenizers 0.11.0 |
|
|