---
language:
- zh
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_1
model-index:
- name: Wisper-Small-zh_test
  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. -->

# Wisper-Small-zh_test

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 16.1 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3867
- Cer: 21.2804

## 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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 2000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Cer      | Validation Loss |
|:-------------:|:------:|:----:|:--------:|:---------------:|
| 2.9388        | 0.6623 | 500  | 102.7090 | 2.9818          |
| 0.5492        | 1.3245 | 1000 | 33.3994  | 0.6020          |
| 0.352         | 1.9868 | 1500 | 0.4214   | 23.2990         |
| 0.2243        | 2.6490 | 2000 | 0.3867   | 21.2804         |


### Framework versions

- Transformers 4.42.0.dev0
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1