whisper-large-v3-it-yodas-only

Fine-tuned openai/whisper-large-v3 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.

Training Details

• Base model: openai/whisper-large-v3
• Dataset: YODAS-Granary Italian (asr_only + ast capped at 200000)
• Steps: 10,000
• Precision: bf16

Usage

Transformers

from transformers import pipeline

pipe = pipeline("automatic-speech-recognition", model="LocalAI-io/whisper-large-v3-it-yodas-only")
result = pipe("audio.mp3", generate_kwargs={"language": "it", "task": "transcribe"})
print(result["text"])

CTranslate2 / faster-whisper (INT8, optimized for CPU)

See: LocalAI-io/whisper-large-v3-it-yodas-only-ct2-int8

Links

• CTranslate2 INT8: LocalAI-io/whisper-large-v3-it-yodas-only-ct2-int8
• Code: github.com/mudler/italian-asr
• LocalAI: github.com/mudler/LocalAI