---
language:
- zh
license: apache-2.0
base_model: openai/whisper-large-v2
tags:
- generated_from_trainer
datasets:
- LeoKuo49/Amitabha
model-index:
- name: whisper-large-amitabha
  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-large-amitabha

This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the Amitabha dataset.
It achieves the following results on the evaluation set:
- Loss: 0.0000
- Cer: 0.4498

## 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: 4000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Cer    |
|:-------------:|:-----:|:----:|:---------------:|:------:|
| 0.0079        | 12.5  | 1000 | 0.0118          | 1.1245 |
| 0.0001        | 25.0  | 2000 | 0.0001          | 0.3036 |
| 0.0           | 37.5  | 3000 | 0.0000          | 0.2699 |
| 0.0           | 50.0  | 4000 | 0.0000          | 0.4498 |


### Framework versions

- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1