---
library_name: transformers
license: apache-2.0
base_model: ivrit-ai/yi-whisper-large-v3
tags:
- generated_from_trainer
metrics:
- wer
model-index:
- name: yi-whisper-large-v3-omnilingual-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. -->

# yi-whisper-large-v3-omnilingual-v1

This model is a fine-tuned version of [ivrit-ai/yi-whisper-large-v3](https://huggingface.co/ivrit-ai/yi-whisper-large-v3) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3867
- Wer Ortho: 0.3832
- Wer: 0.3101

## 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: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- 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: constant_with_warmup
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 100
- num_epochs: 4

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer Ortho | Wer    |
|:-------------:|:------:|:----:|:---------------:|:---------:|:------:|
| 0.2433        | 1.6446 | 100  | 0.3473          | 0.3845    | 0.3281 |
| 0.1093        | 3.2810 | 200  | 0.3867          | 0.3832    | 0.3101 |


### Framework versions

- Transformers 4.48.1
- Pytorch 2.4.0
- Datasets 3.6.0
- Tokenizers 0.21.4