Hugging Face's logo

hishab
/
titu-xcodec2

Text-to-Speech
PyTorch
Safetensors
xcodec2
audio
codec
speech
multilingual
Model card Files
xet
Community
JahidHishab commited on
Commit
0197076
·
verified ·
1 Parent(s): f6c6cc4

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -110,7 +110,7 @@ Reconstruction metrics are computed over 100 samples for English, Japanese, and
110
  - Japanese: 100 Examples (Emilia Dataset @ 24 kHz)
111
  - Bangla: 100 Examples (Inhouse TTS Dataset @ 22.05 kHz)
112
 
113
- | Model | Lang | MCD ↓ | MSE ↑ | SpeechBERTScore ↑ | SpeechBLEU ↑ | SpeechTokenDist ↑ |
114
  |-------------------|------|--------|--------|-------------|--------|-------------|
115
  | **XCODEC** | BN | 2.823 | 0.003 | 0.939 | 0.500 | 0.816 |
116
  | | EN | 3.166 | 0.012 | 0.962 | 0.660 | 0.856 |
 
110
  - Japanese: 100 Examples (Emilia Dataset @ 24 kHz)
111
  - Bangla: 100 Examples (Inhouse TTS Dataset @ 22.05 kHz)
112
 
113
+ | Model | Lang | MCD ↓ | MSE ↓ | SpeechBERTScore ↑ | SpeechBLEU ↑ | SpeechTokenDist ↑ |
114
  |-------------------|------|--------|--------|-------------|--------|-------------|
115
  | **XCODEC** | BN | 2.823 | 0.003 | 0.939 | 0.500 | 0.816 |
116
  | | EN | 3.166 | 0.012 | 0.962 | 0.660 | 0.856 |