TingChen-ppmc
/

whisper-small-Tianjin

Automatic Speech Recognition

Model card Files Files and versions

This is a finetuned version of Whisper-small on Tianjin_Dialect_Conversational_Speech_Corpus

Results

CER: 46.17

WER: 67.65

Chinese Word Error Rate (WER) is based on Jieba Word segmentation

Downloads last month: 7

Safetensors

Model size

0.2B params

Tensor type

F32

·

Model tree for TingChen-ppmc/whisper-small-Tianjin

Base model

openai/whisper-small

Finetuned

(3672)

this model

Dataset used to train TingChen-ppmc/whisper-small-Tianjin