metadata
language: it
license: mit
tags:
- whisper
- automatic-speech-recognition
- italian
- localai
datasets:
- mozilla-foundation/common_voice_25_0
base_model: openai/whisper-base
pipeline_tag: automatic-speech-recognition
whisper-base-it
Fine-tuned openai/whisper-base (74M params) for Italian automatic speech recognition (ASR).
Author: Ettore Di Giacinto
Brought to you by the LocalAI team. This model can be used directly with LocalAI.
Usage with LocalAI
This model is ready to use with LocalAI via the whisperx backend.
Save the following as whisperx-base-it.yaml in your LocalAI models directory:
name: whisperx-base-it
backend: whisperx
known_usecases:
- transcript
parameters:
model: LocalAI-io/whisper-base-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-base-it"
Results
Evaluated on Common Voice 25.0 Italian test set (15,184 samples):
| Step | WER |
|---|---|
| 1000 | 26.5% |
| 2000 | 24.0% |
| 3000 | 22.4% |
| 5000 | 20.6% |
| 7000 | 19.9% |
| 10000 | 19.2% |
Training Details
- Base model: openai/whisper-base (74M 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
Usage
Transformers
from transformers import pipeline
pipe = pipeline("automatic-speech-recognition", model="LocalAI-io/whisper-base-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-base-it-ct2-int8 (79MB).
LocalAI
This model is compatible with LocalAI for local, self-hosted AI inference.
Links
- CTranslate2 INT8: LocalAI-io/whisper-base-it-ct2-int8
- Code: github.com/localai-org/italian-whisper
- LocalAI: github.com/mudler/LocalAI