whisper-tiny-it

Fine-tuned openai/whisper-tiny (39M 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-tiny-it.yaml in your LocalAI models directory:

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:

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

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 (39MB).

LocalAI

This model is compatible with LocalAI for local, self-hosted AI inference.

Links

• Code: github.com/localai-org/italian-whisper
• CTranslate2 INT8: LocalAI-io/whisper-tiny-it-ct2-int8
• LocalAI: github.com/mudler/LocalAI