pongjin/en_corpora_parliament_processed
Viewer โข Updated โข 1.89M โข 15
How to use pongjin/en_with_korean_model_large_960h with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("automatic-speech-recognition", model="pongjin/en_with_korean_model_large_960h") # Load model directly
from transformers import AutoProcessor, AutoModelForCTC
processor = AutoProcessor.from_pretrained("pongjin/en_with_korean_model_large_960h")
model = AutoModelForCTC.from_pretrained("pongjin/en_with_korean_model_large_960h")This model has been referred to the following links
Thanks to patrickvonplaten Patrick von Platen
ํด๋น ๋ชจ๋ธ์ ํ๊ตญ์ธ์ ์์ด ๋ฐํ ์ธ์ ์ฑ๋ฅ ๊ฐ์ ์ ์ํด facebook/wav2vec2-large-960h ๋ก ํ์ธํ๋ํ ๋ชจ๋ธ์ KenLM 5-gram ์ ๋ถ์ธ ASR + LM ๋ชจ๋ธ์ ๋๋ค.
If you want to use LM, you must have kenlm installed https://github.com/kpu/kenlm
pip install https://github.com/kpu/kenlm/archive/master.zip
ํ์ต ๋ฐ์ดํฐ ์ถ์ฒ : https://aiopen.etri.re.kr/voiceModel
transformers==4.24.0
huggingface_hub==0.13.2
| wer | epoch | batch | lr | weight_decay | warmup_steps |
|---|---|---|---|---|---|
| 0.17 | 10 | 16 | 1e-4 | 0.005 | 1000 |