Automatic Speech Recognition
cactus
wannaphong commited on
Commit
6a060c4
·
verified ·
1 Parent(s): 7b1f2cd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -0
README.md CHANGED
@@ -26,6 +26,9 @@ MaprangSTT is a Thai speech-to-Text model built on [Cactus-Compute/whistle](http
26
 
27
  Trained on **1,022.78 hours (594,231 clips)** of curated Thai speech using quantization-aware LoRA (`CQ W4 STE + A8`) and an expanded Thai SentencePiece vocabulary, the final model compiles into a standalone **32.49 MB** `.cact` archive ready for fast on-device CPU/GPU/mobile inference.
28
 
 
 
 
29
  ## Model Summary
30
 
31
  | Property | Value |
 
26
 
27
  Trained on **1,022.78 hours (594,231 clips)** of curated Thai speech using quantization-aware LoRA (`CQ W4 STE + A8`) and an expanded Thai SentencePiece vocabulary, the final model compiles into a standalone **32.49 MB** `.cact` archive ready for fast on-device CPU/GPU/mobile inference.
28
 
29
+ - **GitHub**: [https://github.com/wannaphong/MaprangSTT](https://github.com/wannaphong/MaprangSTT)
30
+ - **In-Browser Web Demo (`cactus-needle`)**: [https://wannaphong.github.io/MaprangSTT/demo](https://wannaphong.github.io/MaprangSTT/demo)
31
+
32
  ## Model Summary
33
 
34
  | Property | Value |