mlboydaisuke commited on
Commit
9b0cf41
·
verified ·
1 Parent(s): 6dd0418

Card: plainer wording

Browse files

- Wording: plainer words for a few other things.

Files changed (1) hide show
  1. README.md +1 -1
README.md CHANGED
@@ -27,7 +27,7 @@ Measured on device (edge-compat, matcha_vocoder_fp16): Raspberry Pi 5 · LiteRT
27
  # Matcha-TTS — LiteRT (on-device, FFT-free, GPU)
28
 
29
  On-device English text-to-speech for Android via LiteRT `CompiledModel`. This is the
30
- **FFT-free** TTS lane: [Matcha-TTS](https://github.com/shivammehta25/Matcha-TTS) pairs a
31
  conditional flow-matching (CFM) acoustic model with a **HiFi-GAN time-domain vocoder**, so
32
  there is **no FFT/iSTFT anywhere** in the synthesis path. 22.05 kHz, LJSpeech voice.
33
 
 
27
  # Matcha-TTS — LiteRT (on-device, FFT-free, GPU)
28
 
29
  On-device English text-to-speech for Android via LiteRT `CompiledModel`. This is the
30
+ **FFT-free** TTS pipeline: [Matcha-TTS](https://github.com/shivammehta25/Matcha-TTS) pairs a
31
  conditional flow-matching (CFM) acoustic model with a **HiFi-GAN time-domain vocoder**, so
32
  there is **no FFT/iSTFT anywhere** in the synthesis path. 22.05 kHz, LJSpeech voice.
33