whisper-large-v3-turbo-it

Fine-tuned openai/whisper-large-v3-turbo (809M params) for Italian ASR.

Author: Ettore Di Giacinto

Brought to you by the LocalAI team.

Usage with LocalAI

This model is ready to use with LocalAI via the whisperx backend.

Save the following as whisperx-large-v3-turbo-it.yaml in your LocalAI models directory:

name: whisperx-large-v3-turbo-it
backend: whisperx
known_usecases:
  - transcript
parameters:
  model: LocalAI-io/whisper-large-v3-turbo-it-ct2-int8
  language: it

Then transcribe audio via the OpenAI-compatible endpoint:

curl http://localhost:8080/v1/audio/transcriptions \
  -H "Content-Type: multipart/form-data" \
  -F file="@audio.mp3" \
  -F model="whisperx-large-v3-turbo-it"

Training Details

• Base model: openai/whisper-large-v3-turbo (809M parameters)
• Dataset: Common Voice 25.0 Italian (173k train, 15k dev, 15k test)
• Steps: 10,000 (batch size 8)
• Precision: bf16 on NVIDIA GB10
• Note: trained with --no-eval; final WER to be measured separately

Usage

```python from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="LocalAI-io/whisper-large-v3-turbo-it") result = pipe("audio.mp3", generate_kwargs={"language": "it", "task": "transcribe"}) ```

Links

• Multi-dataset version: LocalAI-io/whisper-large-v3-turbo-it-multi
• CTranslate2 INT8: LocalAI-io/whisper-large-v3-turbo-it-ct2-int8
• Code: github.com/localai-org/italian-whisper