---
language: it
license: mit
tags:
- whisper
- automatic-speech-recognition
- italian
- ctranslate2
- faster-whisper
- whisperx
- localai
datasets:
- mozilla-foundation/common_voice_25_0
base_model: openai/whisper-tiny
pipeline_tag: automatic-speech-recognition
---

# whisper-tiny-it

Fine-tuned [openai/whisper-tiny](https://huggingface.co/openai/whisper-tiny) (39M params) for Italian automatic speech recognition (ASR).

**Author:** Ettore Di Giacinto

Brought to you by the [LocalAI](https://github.com/mudler/LocalAI) team. This model can be used directly with [LocalAI](https://localai.io).

## Usage with LocalAI

This model is ready to use with [LocalAI](https://localai.io) via the `whisperx` backend.

Save the following as `whisperx-tiny-it.yaml` in your LocalAI models directory:

```yaml
name: whisperx-tiny-it
backend: whisperx
known_usecases:
  - transcript
parameters:
  model: LocalAI-io/whisper-tiny-it-ct2-int8
  language: it
```

Then transcribe audio via the OpenAI-compatible endpoint:

```bash
curl http://localhost:8080/v1/audio/transcriptions \
  -H "Content-Type: multipart/form-data" \
  -F file="@audio.mp3" \
  -F model="whisperx-tiny-it"
```

## Results

Evaluated on Common Voice 25.0 Italian test set (15,184 samples):

| Step | Train Loss | Eval Loss | WER |
|------|-----------|-----------|-----|
| 1000 | — | 0.59 | 37.1% |
| 3000 | 0.42 | 0.47 | 30.8% |
| 5000 | — | 0.43 | 28.7% |
| 10000 | 0.29 | 0.40 | **27.1%** |

## Training Details

- **Base model:** openai/whisper-tiny (39M parameters)
- **Dataset:** Common Voice 25.0 Italian (173k train, 15k dev, 15k test)
- **Steps:** 10,000 (batch size 32, ~1.8 epochs)
- **Learning rate:** 1e-5 with 500 warmup steps
- **Precision:** bf16 on NVIDIA GB10
- **Training time:** ~2 hours

## Usage

### Transformers

```python
from transformers import pipeline

pipe = pipeline("automatic-speech-recognition", model="LocalAI-io/whisper-tiny-it")
result = pipe("audio.mp3", generate_kwargs={"language": "it", "task": "transcribe"})
print(result["text"])
```

### CTranslate2 / faster-whisper

For optimized CPU inference, use the INT8 quantized version: [LocalAI-io/whisper-tiny-it-ct2-int8](https://huggingface.co/LocalAI-io/whisper-tiny-it-ct2-int8) (39MB).

### LocalAI

This model is compatible with [LocalAI](https://github.com/mudler/LocalAI) for local, self-hosted AI inference.

## Links

- **Code:** [github.com/localai-org/italian-whisper](https://github.com/localai-org/italian-whisper)
- **CTranslate2 INT8:** [LocalAI-io/whisper-tiny-it-ct2-int8](https://huggingface.co/LocalAI-io/whisper-tiny-it-ct2-int8)
- **LocalAI:** [github.com/mudler/LocalAI](https://github.com/mudler/LocalAI)