Downloads · 30 days
7
25% of all-time downloads
whisper-korean
Woody113/whisper-korean
whisper-korean is a machine learning model from Woody113. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This is a fine-tuned version of OpenAI's Whisper model for Korean speech recognition.
All-time downloads
28
Public
Parameters
72.6M
290 MB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors290 MB · 99%
At a glance
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Jul 27, 2025
- Updated
- Jul 27, 2025
- SHA
- 2d981053
Base models
Model card
From the Hugging Face model README
Whisper Korean Fine-tuned Model
This is a fine-tuned version of OpenAI's Whisper model for Korean speech recognition.
Usage
from transformers import WhisperForConditionalGeneration, WhisperProcessor
import torch
model = WhisperForConditionalGeneration.from_pretrained("Woody113/whisper-korean")
processor = WhisperProcessor.from_pretrained("Woody113/whisper-korean")
# 음성 파일 처리 예제
# audio_input = ... (your audio data)
# input_features = processor(audio_input, sampling_rate=16000, return_tensors="pt").input_features
# predicted_ids = model.generate(input_features)
# transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
Training Details
- Base model: OpenAI Whisper
- Language: Korean
- Fine-tuning dataset: [Dataset description]
- Training parameters: [Training details]
- Type
- whisper
- License
- apache-2.0
- Languages
- ko
- Created
- Jul 27, 2025
- Updated
- Jul 27, 2025