RL10x commited on
Commit
d2ec84d
·
verified ·
1 Parent(s): 4a43f91

Model card: remove the model table

Browse files
Files changed (1) hide show
  1. README.md +1 -16
README.md CHANGED
@@ -33,22 +33,7 @@ filter) makes the waveform directly. No separate neural vocoder is needed.
33
  | `tiny_voca_hindi.pt` | PyTorch checkpoint (state dict + config), after 100k training steps | 38.9 MB |
34
  | `config.json` | the model configuration | |
35
 
36
- The inference code is **not included in this repository**. The sections below describe the model so it can be used or
37
- re-implemented.
38
-
39
- ## Model
40
-
41
- | | |
42
- |---|---|
43
- | Parameters | 9,711,755 |
44
- | Input | phoneme ids (70 symbols, below), a nasalization flag per phoneme, a style id |
45
- | Output | 24 kHz mono audio |
46
- | Text encoder | 4 transformer blocks (256 channels, 4 heads, rotary attention, depthwise conv k=7, FFN 1024) |
47
- | Durations | 2 conv layers → frames per phoneme (log scale) + a pause/no-pause logit for pause-capable tokens |
48
- | Prosody | 2 transformer blocks over frames → log F0, voicing, energy per 10.7 ms frame |
49
- | Acoustic | 6 transformer blocks → filter cepstra and gains for the harmonic and noise branches |
50
- | Synthesizer | band-limited pulse train at the predicted pitch + white noise, each filtered per frame (complex cepstrum, STFT overlap-add) |
51
- | Styles | neutral, conv, happy, sad, anger, fear, surprise, disgust |
52
 
53
  ## Training
54
 
 
33
  | `tiny_voca_hindi.pt` | PyTorch checkpoint (state dict + config), after 100k training steps | 38.9 MB |
34
  | `config.json` | the model configuration | |
35
 
36
+ The inference code is **not included in this repository**.
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
37
 
38
  ## Training
39