---
tags:
- generated_from_trainer
- 4-grams
- ASR with lm
- ASR with 4-gram
- speech-to-text with lm
model-index:
- name: wav2vec2-large-asr-th-2
  results: []
datasets:
- mozilla-foundation/common_voice_10_0
language:
- th
metrics:
- cer
- wer
library_name: transformers
pipeline_tag: automatic-speech-recognition
---

<!-- 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-asr-th-2

This model was trained from scratch on the None dataset.
It achieves the following results on the evaluation set:
- eval_loss: 0.1819
- eval_wer: 0.3346
- eval_cer: 0.0910
- eval_runtime: 735.0436
- eval_samples_per_second: 13.822
- eval_steps_per_second: 1.728
- epoch: 0.95
- step: 4000

## 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: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 3
- total_train_batch_size: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP

### Framework versions

- Transformers 4.27.4
- Pytorch 1.13.1+cu116
- Datasets 2.11.0
- Tokenizers 0.13.2