---
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: openai/whisper-large-v3
datasets:
- common_voice_17_0
model-index:
- name: whisper-large3-mon
  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-large3-mon

This model is a fine-tuned version of [openai/whisper-large-v3](https://huggingface.co/openai/whisper-large-v3) on the common_voice_17_0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.4062

## 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: 0.001
- train_batch_size: 18
- eval_batch_size: 18
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 2.0
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 1.103         | 0.5882 | 100  | 0.7301          |
| 0.5508        | 1.1765 | 200  | 0.5630          |
| 0.4061        | 1.7647 | 300  | 0.4062          |


### Framework versions

- PEFT 0.11.2.dev0
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1