---
language:
- ro
license: apache-2.0
base_model: openai/whisper-medium
tags:
- hf-asr-leaderboard
- generated_from_trainer
datasets:
- mozilla-foundation/common_voice_16_1
metrics:
- wer
model-index:
- name: Whisper Medium Ro - Sarbu Vlad
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: Common Voice 16.1
      type: mozilla-foundation/common_voice_16_1
      args: 'config: ro, split: test'
    metrics:
    - name: Wer
      type: wer
      value: 12.451220618930938
---

<!-- 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 Ro - Sarbu Vlad

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 16.1 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1471
- Wer: 12.4512

## 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: 16
- eval_batch_size: 16
- seed: 42
- distributed_type: multi-GPU
- num_devices: 3
- total_train_batch_size: 48
- total_eval_batch_size: 48
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 1500
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| 0.3367        | 0.98  | 250  | 0.1873          | 16.5290 |
| 0.1131        | 1.96  | 500  | 0.1383          | 13.7792 |
| 0.0597        | 2.94  | 750  | 0.1306          | 12.3695 |
| 0.0311        | 3.92  | 1000 | 0.1329          | 12.2758 |
| 0.0168        | 4.9   | 1250 | 0.1410          | 12.5117 |
| 0.0102        | 5.88  | 1500 | 0.1471          | 12.4512 |


### Framework versions

- Transformers 4.37.2
- Pytorch 2.2.0
- Datasets 2.17.0
- Tokenizers 0.15.1