|
|
---
|
|
|
library_name: transformers
|
|
|
license: apache-2.0
|
|
|
base_model: openai/whisper-medium.en
|
|
|
tags:
|
|
|
- generated_from_trainer
|
|
|
model-index:
|
|
|
- name: whisper-medium.en-merged_dataset
|
|
|
results: []
|
|
|
---
|
|
|
|
|
|
<!-- 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. -->
|
|
|
|
|
|
# whisper-medium.en-merged_dataset
|
|
|
|
|
|
This model is a fine-tuned version of [openai/whisper-medium.en](https://huggingface.co/openai/whisper-medium.en) on the None dataset.
|
|
|
It achieves the following results on the evaluation set:
|
|
|
- Cer: 890.9343
|
|
|
- Loss: 0.5805
|
|
|
|
|
|
## 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: 1
|
|
|
- eval_batch_size: 1
|
|
|
- seed: 42
|
|
|
- gradient_accumulation_steps: 16
|
|
|
- total_train_batch_size: 16
|
|
|
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
|
|
- lr_scheduler_type: linear
|
|
|
- num_epochs: 3
|
|
|
- mixed_precision_training: Native AMP
|
|
|
|
|
|
### Training results
|
|
|
|
|
|
| Training Loss | Epoch | Step | Cer | Validation Loss |
|
|
|
|:-------------:|:------:|:----:|:--------:|:---------------:|
|
|
|
| 3.1316 | 0.2626 | 500 | 327.6237 | 1.4389 |
|
|
|
| 1.2083 | 0.5252 | 1000 | 456.3455 | 0.9819 |
|
|
|
| 0.9269 | 0.7878 | 1500 | 737.9578 | 0.8079 |
|
|
|
| 0.7618 | 1.0504 | 2000 | 966.5418 | 0.7155 |
|
|
|
| 0.5428 | 1.3130 | 2500 | 665.7924 | 0.6660 |
|
|
|
| 0.5139 | 1.5756 | 3000 | 899.3139 | 0.6320 |
|
|
|
| 0.4948 | 1.8382 | 3500 | 965.0479 | 0.6049 |
|
|
|
| 0.4122 | 2.1008 | 4000 | 942.7040 | 0.5902 |
|
|
|
| 0.3145 | 2.3634 | 4500 | 969.4258 | 0.5819 |
|
|
|
| 0.2576 | 2.6261 | 5000 | 890.9343 | 0.5805 |
|
|
|
|
|
|
|
|
|
### Framework versions
|
|
|
|
|
|
- Transformers 4.51.0
|
|
|
- Pytorch 2.7.1+cu128
|
|
|
- Datasets 3.6.0
|
|
|
- Tokenizers 0.21.1
|
|
|
|
