antonvinny/whisper-tiny-anton
By antonvinny · ↓ 0 · ♥ 0 · Updated 2025-01-15
What's in this repo
This page lists the files in antonvinny/whisper-tiny-anton, including decoder_model.onnx, decoder_with_past_model.onnx, encoder_model.onnx and more.
- 7 ONNX models (.onnx files)
- 34 files, including 18 .json, 7 .onnx, 2 .txt, 1 .md, 1 .safetensors, 1 .0
- Last updated 2025-01-15
ONNX files
| File | Size | Download |
|---|---|---|
| decoder_model.onnx | — | Download |
| decoder_with_past_model.onnx | — | Download |
| encoder_model.onnx | — | Download |
| onnx/decoder_model_merged_quantized.onnx | — | Download |
| onnx/decoder_model_quantized.onnx | — | Download |
| onnx/decoder_with_past_model_quantized.onnx | — | Download |
| onnx/encoder_model_quantized.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
Whisper Tiny En - AntonVinny
This model is a fine-tuned version of openai/whisper-tiny on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0000
- Wer: 2.4952
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: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- 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 | Wer |
|---|---|---|---|---|
| 0.0001 | 250.0 | 1000 | 0.0002 | 2.5912 |
| 0.0001 | 500.0 | 2000 | 0.0001 | 2.4952 |
| 0.0 | 750.0 | 3000 | 0.0000 | 2.4952 |
| 0.0 | 1000.0 | 4000 | 0.0000 | 2.4952 |
Framework versions
- Transformers 4.48.0
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0
Model info
Created: 2025-01-12
Updated: 2025-01-15
View on Hugging Face