openai/large_v2_nan_tw_so_short_30s
This model is a fine-tuned version of 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: 63.42
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
- Downloads last month
- 1
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.
Model tree for thomas0104/large_v2_nan_tw_so_short_30s
Base model
openai/whisper-large-v2Dataset used to train thomas0104/large_v2_nan_tw_so_short_30s
Evaluation results
- Cer on thomas0104/nan_tw_soap_opera nan-twtest set self-reported63.420