---
library_name: transformers
language:
- zh
base_model: whucedar/amoros_spec_01_train_20-medium_1000_8
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- whucedar/amoros_spec_02-medium
metrics:
- wer
model-index:
- name: amoros_spec_02-medium
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: amoros_spec_02
      type: whucedar/amoros_spec_02-medium
      args: 'config: zh, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 438.75
---

<!-- 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. -->

# amoros_spec_02-medium

This model is a fine-tuned version of [whucedar/amoros_spec_01_train_20-medium_1000_8](https://huggingface.co/whucedar/amoros_spec_01_train_20-medium_1000_8) on the amoros_spec_02 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.5581
- Wer: 438.75

## 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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 1000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.0001        | 100.0 | 1000 | 0.5581          | 438.75 |


### Framework versions

- Transformers 4.52.3
- Pytorch 2.7.0+cu126
- Datasets 3.6.0
- Tokenizers 0.21.1