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
6
Safetensors
Model size
242M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.

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

Finetuned
(2272)
this model

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