|
--- |
|
language: |
|
- ha |
|
license: apache-2.0 |
|
tags: |
|
- automatic-speech-recognition |
|
- mozilla-foundation/common_voice_8_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-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the MOZILLA-FOUNDATION/COMMON_VOICE_8_0 - HA dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7424 |
|
- Wer: 0.6190 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- total_train_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 2000 |
|
- num_epochs: 90.0 |
|
- mixed_precision_training: Native AMP |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 2.721 | 16.66 | 500 | 2.6876 | 1.0 | |
|
| 1.2944 | 33.33 | 1000 | 0.6482 | 0.7135 | |
|
| 1.0515 | 49.98 | 1500 | 0.6645 | 0.6754 | |
|
| 0.9153 | 66.66 | 2000 | 0.7649 | 0.6936 | |
|
| 0.7056 | 83.33 | 2500 | 0.8048 | 0.6756 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.17.0.dev0 |
|
- Pytorch 1.10.2+cu113 |
|
- Datasets 1.18.4.dev0 |
|
- Tokenizers 0.11.0 |
|
|