---
library_name: peft
language:
- fa
license: apache-2.0
base_model: openai/whisper-medium
tags:
- generated_from_trainer
datasets:
- srezas/farsi_voice_dataset
model-index:
- name: Whisper medium Fa - SRezaS
  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 Fa - SRezaS

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Persian Custom Split Common Voice 17.0 + Fleurs dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1636

## 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: 0.0001
- train_batch_size: 16
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- optimizer: Use 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: 50
- num_epochs: 2
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch  | Step | Validation Loss |
|:-------------:|:------:|:----:|:---------------:|
| 0.1791        | 1.0    | 4230 | 0.1811          |
| 0.1304        | 1.9996 | 8458 | 0.1636          |


### Framework versions

- PEFT 0.13.3.dev0
- Transformers 4.47.0
- Pytorch 2.5.1+cu124
- Datasets 3.1.0
- Tokenizers 0.21.0