Downloads · 30 days
104
7% of all-time downloads
whisper-medium-korean-ggml
royshilkrot/whisper-medium-korean-ggml
whisper-medium-korean-ggml is a automatic speech recognition model from royshilkrot. Use it when you need speech turned into text. The card lists the license as apache-2.0.
This model is a fine-tune of OpenAI's Whisper Medium model (https://huggingface.co/openai/whisper-medium) over the following Korean datasets:
All-time downloads
1.5K
Public
Parameters
764M
4.6 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors3.1 GB · 67%
At a glance
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Model type
- whisper
- Access
- Public
- Created
- Oct 2, 2024
- Updated
- Oct 30, 2024
- SHA
- 61a8ee3c
Base models
Model card
From the Hugging Face model README
This model is a fine-tune of OpenAI's Whisper Medium model (https://huggingface.co/openai/whisper-medium) over the following Korean datasets:
- https://huggingface.co/datasets/Junhoee/STT_Korean_Dataset_80000
- https://huggingface.co/datasets/Bingsu/zeroth-korean
Combined they have roughly 102k sentences.
This is the last checkpoint which has achieved ~16 WER (down from ~24 WER).
Training was 10,000 iterations.
- Task
- Automatic Speech Recognition
- Type
- whisper
- License
- apache-2.0
- Languages
- ko
- Created
- Oct 2, 2024
- Updated
- Oct 30, 2024