---
language:
- zh
license: apache-2.0
tags:
- generated_from_trainer
base_model: openai/whisper-tiny
datasets:
- mozilla-foundation/common_voice_16_1
model-index:
- name: Whisper Tiny chinese - VingeNie
  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. -->

# Whisper Tiny chinese - VingeNie

This model is a fine-tuned version of [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) on the Common Voice 16.1 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.2299
- Cer Ortho: 12.3059
- Cer: 9.6019

## 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: 64
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- training_steps: 2400
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Cer Ortho | Cer     |
|:-------------:|:------:|:----:|:---------------:|:---------:|:-------:|
| 0.3624        | 0.4762 | 400  | 0.3612          | 20.5899   | 14.9427 |
| 0.2975        | 0.9524 | 800  | 0.2915          | 16.1479   | 12.4655 |
| 0.1978        | 1.4286 | 1200 | 0.2650          | 14.6830   | 11.2300 |
| 0.1852        | 1.9048 | 1600 | 0.2438          | 13.5687   | 10.3808 |
| 0.1172        | 2.3810 | 2000 | 0.2361          | 12.6794   | 9.9609  |
| 0.1097        | 2.8571 | 2400 | 0.2299          | 12.3059   | 9.6019  |


### Framework versions

- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1