# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("royshilkrot/whisper-large-v3-turbo-korean-ggml")
model = AutoModelForSpeechSeq2Seq.from_pretrained("royshilkrot/whisper-large-v3-turbo-korean-ggml", device_map="auto")Quick Links
This model is a fine-tune of OpenAI's Whisper Large v3 Turbo model (https://huggingface.co/openai/whisper-large-v3-turbo) 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.
- Downloads last month
- 39
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="royshilkrot/whisper-large-v3-turbo-korean-ggml")