NbAiLab/salmon-whisper-large-smj-lr7e-5
By NbAiLab · ↓ 9 · ♥ 0 · Updated 2023-12-07
What's in this repo
This page lists the files in NbAiLab/salmon-whisper-large-smj-lr7e-5, including decoder_model.onnx, decoder_with_past_model.onnx, encoder_model.onnx.
- 3 ONNX models (.onnx files)
- 37 files, including 19 .json, 4 .bin, 3 .txt, 3 .onnx, 3 .onnx_data, 1 .md
- Last updated 2023-12-07
ONNX files
| File | Size | Download |
|---|---|---|
| onnx/decoder_model.onnx | — | Download |
| onnx/decoder_with_past_model.onnx | — | Download |
| onnx/encoder_model.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
salmon-whisper-large-smj-lr7e-5
This model is a fine-tuned version of openai/whisper-large-v2 on the NbAiLab/salmon-asr-smj dataset.
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: 7e-05
- lr_scheduler_type: linear
- per_device_train_batch_size: 6
- total_train_batch_size_per_node: 48
- total_train_batch_size: 48
- total_optimization_steps: 100,000
- starting_optimization_step: None
- finishing_optimization_step: 100,000
- num_train_dataset_workers: 32
- num_hosts: 1
- total_num_training_examples: 4,800,000
- steps_per_epoch: 385
- num_beams: None
- weight_decay: 0.01
- adam_beta1: 0.9
- adam_beta2: 0.98
- adam_epsilon: 1e-06
- dropout: True
- bpe_dropout_probability: 0.2
- activation_dropout_probability: 0.1
Training results
| step | validation_loss | train_loss | validation_wer | validation_cer | validation_exact_wer | validation_exact_cer |
|---|---|---|---|---|---|---|
| 0 | 4.2254 | 4.7016 | 112.7660 | 59.8700 | 108.1117 | 62.0594 |
| 10000 | 0.8352 | 0.3801 | 18.0851 | 5.5037 | 22.2074 | 6.0546 |
| 20000 | 1.1701 | 0.2580 | 15.2926 | 5.0569 | 17.8191 | 5.4770 |
| 30000 | 1.0861 | 0.2306 | 14.4947 | 4.6304 | 17.2872 | 4.9393 |
| 40000 | 1.0137 | 0.2168 | 14.2287 | 4.3461 | 16.7553 | 4.6206 |
| 50000 | 1.1032 | 0.2313 | 13.6968 | 3.8993 | 16.0904 | 4.1625 |
| 60000 | 1.2158 | 0.2121 | 13.6968 | 4.2648 | 16.0904 | 4.5808 |
| 70000 | 1.1595 | 0.2567 | 12.3670 | 3.7977 | 14.7606 | 4.1028 |
| 80000 | 1.1889 | 0.2420 | 12.5 | 4.0008 | 14.7606 | 4.2621 |
| 90000 | 1.1761 | 0.2039 | 12.6330 | 4.0211 | 14.8936 | 4.3218 |
Framework versions
- Transformers 4.35.0
- Datasets 2.14.6
- Tokenizers 0.14.1
Model info
Created: 2023-11-09
Updated: 2023-12-07
View on Hugging Face