Downloads · 30 days
12
10% of all-time downloads
manohar03/unsloth-whisper-large-v3-turbo-pruna-smashed
unsloth-whisper-large-v3-turbo-pruna-smashed is a automatic speech recognition model from manohar03. Use it when you need speech turned into text. It is set up for pruna. The card lists the license as apache-2.0.
Pruna-optimized version of Whisper Large V3 Turbo. Compressed with cwhisper compiler for faster inference and lower VRAM usage, while maintaining the same transcription quality.
Downloads · 30 days
12
10% of all-time downloads
All-time downloads
123
Public
Parameters
809M
1.6 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors1.6 GB · 100%
From the Hugging Face model README
Pruna-optimized version of Whisper Large V3 Turbo.
Compressed with c_whisper compiler for faster inference and lower VRAM usage, while maintaining the same transcription quality.
Best performance (Pruna runtime):
from pruna import PrunaModel
model = PrunaModel.from_pretrained("manohar03/unsloth-whisper-large-v3-turbo-pruna-smashed")
result = model("audio.wav")
Standard Transformers:
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor
model = AutoModelForSpeechSeq2Seq.from_pretrained("manohar03/unsloth-whisper-large-v3-turbo-pruna-smashed")
processor = AutoProcessor.from_pretrained("manohar03/unsloth-whisper-large-v3-turbo-pruna-smashed")
✅ Tested on Google Colab T4 GPU
Dataset: librispeech_asr test-clean (15%)
Device: T4 GPU
Successfully transcribed 2 hours of audio (sam_altman_lex_podcast_367.flac) in under 3 minutes using minimal GPU.
transformers and pruna APIs.