whisper-tiny-it-multi-yodas-asr_only-nocv

Fine-tuned openai/whisper-tiny 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-tiny
• Dataset: MLS + VoxPopuli + YODAS-Granary (asr_only) Italian
• Steps: 10,000
• Precision: bf16

Usage

Transformers

from transformers import pipeline

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

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

See: LocalAI-io/whisper-tiny-it-multi-yodas-asr_only-nocv-ct2-int8

Links

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