Downloads · 30 days
9
25% of all-time downloads
whisper-large-v3-encoder
huseinzol05/whisper-large-v3-encoder
whisper-large-v3-encoder is a machine learning model from huseinzol05. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
All-time downloads
36
Public
Parameters
637M
2.5 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors2.5 GB · 100%
At a glance
- Library
- transformers
- Model type
- whisper
- Access
- Public
- Created
- May 28, 2025
- Updated
- Jul 24, 2025
- SHA
- 3f0ead81
Model card
From the Hugging Face model README
whisper-large-v3-encoder
How to
from transformers.models.whisper.modeling_whisper import WhisperEncoder
from transformers import AutoFeatureExtractor
import torch
import librosa
encoder = WhisperEncoder.from_pretrained(
'huseinzol05/whisper-large-v3-encoder',
torch_dtype = torch.float16).cuda()
feature_extractor = AutoFeatureExtractor.from_pretrained('openai/whisper-large-v3')
y, sr = librosa.load('audio.mp3', sr = 16000)
input_ids = feature_extractor(y, return_tensors = 'pt', sampling_rate = feature_extractor.sampling_rate)
input_ids['input_features'] = input_ids['input_features'].to(torch.float16).cuda()
encoder(**input_ids)
- Library
- transformers
- Type
- whisper
- Created
- May 28, 2025
- Updated
- Jul 24, 2025