Configuration Parsing
Warning:
In adapter_config.json: "peft.task_type" must be a string
whisper-small-CV16-GF-AS-jp
This model is a fine-tuned version of openai/whisper-small on the common_voice_16_0 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7695 This model is a fine-tuned version of openai/whisper-small on the google/fleurs dataset. This model is a fine-tuned version of openai/whisper-small on the joujiboi/japanese-anime-speech dataset.
Model description
3 concantenated datasets LoRA peft on a windows 10 no linux. (Work in progress- this is a test run)
Intended uses & limitations
Test run for large model.
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 0.001
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 500
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
0.3266 | 1.0 | 500 | 0.7695 |
Framework versions
- PEFT 0.8.2
- Transformers 4.38.0.dev0
- Pytorch 2.2.0+cu118
- Datasets 2.16.2.dev0
- Tokenizers 0.15.1
- Downloads last month
- 0