|
--- |
|
license: cc-by-nc-4.0 |
|
base_model: facebook/mms-1b-all |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- common_voice_13_0 |
|
metrics: |
|
- wer |
|
model-index: |
|
- name: wav2vec2-large-mms-1b-kazakh-bache |
|
results: |
|
- task: |
|
name: Automatic Speech Recognition |
|
type: automatic-speech-recognition |
|
dataset: |
|
name: common_voice_13_0 |
|
type: common_voice_13_0 |
|
config: kk |
|
split: test |
|
args: kk |
|
metrics: |
|
- name: Wer |
|
type: wer |
|
value: 0.28966942148760333 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# wav2vec2-large-mms-1b-kazakh-bache |
|
|
|
This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co./facebook/mms-1b-all) on the common_voice_13_0 dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.2490 |
|
- Wer: 0.2897 |
|
|
|
## 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: 0.001 |
|
- train_batch_size: 16 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 100 |
|
- num_epochs: 4 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Wer | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:| |
|
| 6.477 | 1.92 | 100 | 0.2687 | 0.3128 | |
|
| 0.2077 | 3.85 | 200 | 0.2490 | 0.2897 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.0.dev0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.13.3 |
|
|
