Downloads · 30 days
2
4% of all-time downloads
whisper-medium-it-yodas-only
LocalAI-io/whisper-medium-it-yodas-only
whisper-medium-it-yodas-only is a automatic speech recognition model from LocalAI-io. Use it when you need speech turned into text. The card lists the license as mit.
Fine-tuned openai/whisper-medium for Italian automatic speech recognition (ASR).
All-time downloads
52
Public
Parameters
764M
3.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- License
- mit
- Model type
- whisper
- Access
- Public
- Created
- May 2, 2026
- Updated
- May 24, 2026
- SHA
- 4250a941
Base models
Model card
From the Hugging Face model README
whisper-medium-it-yodas-only
Fine-tuned openai/whisper-medium 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-medium
- 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-medium-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-medium-it-yodas-only-ct2-int8
Links
- CTranslate2 INT8: LocalAI-io/whisper-medium-it-yodas-only-ct2-int8
- Code: github.com/mudler/italian-asr
- LocalAI: github.com/mudler/LocalAI
- Task
- Automatic Speech Recognition
- Type
- whisper
- License
- mit
- Languages
- it
- Created
- May 2, 2026
- Updated
- May 24, 2026