# Load model directly
from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq
processor = AutoProcessor.from_pretrained("TingChen-ppmc/whisper-small-Nanchang")
model = AutoModelForSpeechSeq2Seq.from_pretrained("TingChen-ppmc/whisper-small-Nanchang", device_map="auto")Quick Links
This is a finetuned version of Whisper-small on Nanchang_Dialect_Conversational_Speech_Corpus
Results
CER: 71.83
WER: 84.34
Chinese Word Error Rate (WER) is based on Jieba Word segmentation
- Downloads last month
- 5
Model tree for TingChen-ppmc/whisper-small-Nanchang
Base model
openai/whisper-small
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="TingChen-ppmc/whisper-small-Nanchang")