fractalego commited on
Commit
3720e66
1 Parent(s): e54d2c1

Create README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ Personal speech to text model
2
+
3
+ Speech to Text models often do not understand my accent, so I fine tuned this one from "distil-whisper/distil-medium.en" using about 1000 recordings of my voice, comprising of about 2h of recordings. The system goes from ~12% WER to ~8% WER.
4
+
5
+ Do not download unless you have exactly my accent (North-East Italy).