TingChen-ppmc commited on
Commit
6e01064
1 Parent(s): 44ccc61

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +19 -0
README.md CHANGED
@@ -1,3 +1,22 @@
1
  ---
 
 
2
  license: apache-2.0
 
 
 
 
 
 
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ language:
3
+ - ch
4
  license: apache-2.0
5
+ base_model: openai/whisper-small
6
+ datasets:
7
+ - TingChen-ppmc/Changsha_Dialect_Conversational_Speech_Corpus
8
+ metrics:
9
+ - wer
10
+ - cer
11
  ---
12
+
13
+
14
+ This is a finetuned version of [Whisper-small](openai/whisper-small) on [Changsha_Dialect_Conversational_Speech_Corpus](https://huggingface.co/datasets/TingChen-ppmc/Changsha_Dialect_Conversational_Speech_Corpus)
15
+
16
+ # Results
17
+
18
+ CER: 37.77
19
+
20
+ WER: 66.84
21
+
22
+ Chinese Word Error Rate (WER) is based on [Jieba](https://github.com/fxsjy/jieba) Word segmentation