---
language:
- it
license: apache-2.0
tags:
- generated_from_trainer
base_model: openai/whisper-medium
datasets:
- mozilla-foundation/common_voice_17_0
metrics:
- wer
model-index:
- name: Whisper Medium it
  results:
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: Common Voice 17.0
      type: mozilla-foundation/common_voice_17_0
      config: it
      split: test
      args: it
    metrics:
    - type: wer
      value: 5.709779804285139
      name: Wer
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: google/fleurs
      type: google/fleurs
      config: it_it
      split: test
    metrics:
    - type: wer
      value: 4.47
      name: WER
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: facebook/multilingual_librispeech
      type: facebook/multilingual_librispeech
      config: italian
      split: test
    metrics:
    - type: wer
      value: 17.25
      name: WER
  - task:
      type: automatic-speech-recognition
      name: Automatic Speech Recognition
    dataset:
      name: facebook/voxpopuli
      type: facebook/voxpopuli
      config: it
      split: test
    metrics:
    - type: wer
      value: 18.75
      name: WER
---

<!-- 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 it

This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 17.0 dataset.
It achieves the following results on the evaluation set:
- Loss: 0.1462
- Wer: 5.7098

## 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: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- training_steps: 5000

### Training results

| Training Loss | Epoch  | Step | Validation Loss | Wer    |
|:-------------:|:------:|:----:|:---------------:|:------:|
| 0.1755        | 0.1730 | 1000 | 0.1974          | 8.0595 |
| 0.157         | 0.3461 | 2000 | 0.1776          | 7.1199 |
| 0.1287        | 0.5191 | 3000 | 0.1622          | 6.5201 |
| 0.1287        | 0.6922 | 4000 | 0.1521          | 5.9863 |
| 0.1168        | 0.8652 | 5000 | 0.1462          | 5.7098 |


### Framework versions

- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1