---
library_name: transformers
language:
- ro
license: apache-2.0
base_model: openai/whisper-small
tags:
- generated_from_trainer
datasets:
- IoanaLiviaPopescu/RealVoiceSynthVoice-800-1-Standard-B
metrics:
- wer
model-index:
- name: IoanaLiviaPopescu/IoanaLiviaPopescu/real-data-synth-data-800-1-Standard-B-whisper-small-v0
  results:
  - task:
      name: Automatic Speech Recognition
      type: automatic-speech-recognition
    dataset:
      name: IoanaLiviaPopescu/RealVoiceSynthVoice-800-1-Standard-B
      type: IoanaLiviaPopescu/RealVoiceSynthVoice-800-1-Standard-B
      config: default
      split: test
      args: 'split: validation'
    metrics:
    - name: Wer
      type: wer
      value: 17.517978978425226
---

<!-- 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. -->

# IoanaLiviaPopescu/IoanaLiviaPopescu/real-data-synth-data-800-1-Standard-B-whisper-small-v0

This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the IoanaLiviaPopescu/RealVoiceSynthVoice-800-1-Standard-B dataset.
It achieves the following results on the evaluation set:
- Loss: 0.3794
- Wer: 17.5180

## 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: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
- mixed_precision_training: Native AMP

### Training results

| Training Loss | Epoch | Step | Validation Loss | Wer     |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
| No log        | 0     | 0    | 0.6024          | 27.8812 |
| 0.3199        | 1.0   | 38   | 0.4198          | 18.3293 |
| 0.1321        | 2.0   | 76   | 0.3836          | 17.8130 |
| 0.0735        | 3.0   | 114  | 0.3794          | 17.5180 |
| 0.0457        | 4.0   | 152  | 0.3961          | 17.7024 |
| 0.0331        | 5.0   | 190  | 0.4020          | 17.7761 |


### Framework versions

- Transformers 4.51.3
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1