This is a finetuned version of Whisper-small on Shanghai_Dialect_Conversational_Speech_Corpus

Results

CER: 56.07

WER: 75.62

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

Downloads last month
4
Safetensors
Model size
242M params
Tensor type
F32
·
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and the model is not deployed on the HF Inference API.

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

Finetuned
(2237)
this model

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