---
language:
- zh
license: apache-2.0
tags:
- whisper-event
- generated_from_trainer
datasets:
- thomas0104/nan_tw_soap_opera
metrics:
- wer
model-index:
- name: openai/whisper-large-v2
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: thomas0104/nan_tw_soap_opera nan-tw
      type: thomas0104/nan_tw_soap_opera
      config: nan-tw
      split: test
    metrics:
    - name: Wer
      type: wer
      value: 343.562937357727
---

<!-- 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. -->

# openai/large_v2_nan_tw_so_short_30s

This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the thomas0104/nan_tw_soap_opera nan-tw dataset.
It achieves the following results on the evaluation set:
- Loss: 1.3322
- Wer: 343.5629
- Cer: 416.4573

## 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: 2
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- training_steps: 1000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer      | Cer      |
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|
| 1.1133        | 1.0   | 1000 | 1.3322          | 343.5629 | 416.4573 |


### Framework versions

- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu117
- Datasets 2.8.0
- Tokenizers 0.13.2