---
library_name: transformers
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- bigcgen
metrics:
- wer
model-index:
- name: whisper-medium-bigcgen-male-5hrs-62
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: bigcgen
      type: bigcgen
    metrics:
    - name: Wer
      type: wer
      value: 0.516229862947824
---

<!-- 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-bigcgen-male-5hrs-62

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the bigcgen dataset.
It achieves the following results on the evaluation set:
- Loss: 0.6629
- Wer: 0.5162

## 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: 62
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- 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
- lr_scheduler_warmup_steps: 500
- training_steps: 5000
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 0.956         | 0.6211 | 200  | 0.8871          | 0.6444 |
| 0.6779        | 1.2422 | 400  | 0.7327          | 0.5585 |
| 0.5879        | 1.8634 | 600  | 0.6629          | 0.5162 |
| 0.4268        | 2.4845 | 800  | 0.6734          | 0.5006 |
| 0.1979        | 3.1056 | 1000 | 0.7147          | 0.4766 |
| 0.2338        | 3.7267 | 1200 | 0.7034          | 0.4869 |
| 0.1014        | 4.3478 | 1400 | 0.7554          | 0.4879 |


### Framework versions

- Transformers 4.53.0.dev0
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.0