---
base_model: openai/whisper-large-v2
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: whisper-large-v2-ft-cv16-1__car350_tms-good-30-250504-v1
  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-large-v2-ft-cv16-1__car350_tms-good-30-250504-v1

This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1000

## 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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 64
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.2
- num_epochs: 10
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 4.0498        | 1.0   | 177  | 1.2594          |
| 0.3113        | 2.0   | 354  | 0.1046          |
| 0.1107        | 3.0   | 531  | 0.0912          |
| 0.0852        | 4.0   | 708  | 0.0880          |
| 0.0688        | 5.0   | 885  | 0.0886          |
| 0.0563        | 6.0   | 1062 | 0.0911          |
| 0.0469        | 7.0   | 1239 | 0.0928          |
| 0.0397        | 8.0   | 1416 | 0.0955          |
| 0.0341        | 9.0   | 1593 | 0.0982          |
| 0.0304        | 10.0  | 1770 | 0.1000          |


### Framework versions

- PEFT 0.13.0
- Transformers 4.45.1
- Pytorch 2.5.0+cu124
- Datasets 2.21.0
- Tokenizers 0.20.0