hello_world / README.md
ugshanyu's picture
update model card README.md
aa934ab
---
license: apache-2.0
tags:
- generated_from_trainer
datasets:
- common_voice
metrics:
- wer
model-index:
- name: hello_world
results:
- task:
name: Automatic Speech Recognition
type: automatic-speech-recognition
dataset:
name: common_voice
type: common_voice
config: mn
split: test
args: mn
metrics:
- name: Wer
type: wer
value: 0.4679207811551829
---
<!-- 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. -->
# hello_world
This model is a fine-tuned version of [tugstugi/wav2vec2-large-xlsr-53-mongolian](https://huggingface.co/tugstugi/wav2vec2-large-xlsr-53-mongolian) on the common_voice dataset.
It achieves the following results on the evaluation set:
- Loss: 0.8235
- Wer: 0.4679
## 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: 2
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
### Training results
| Training Loss | Epoch | Step | Validation Loss | Wer |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 2.1725 | 6.78 | 400 | 0.8343 | 0.5449 |
| 0.1406 | 13.56 | 800 | 0.8587 | 0.5158 |
| 0.1013 | 20.34 | 1200 | 0.8260 | 0.4990 |
| 0.0701 | 27.12 | 1600 | 0.8235 | 0.4679 |
### Framework versions
- Transformers 4.30.1
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3