Instructions to use litert-community/Matcha-TTS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT
How to use litert-community/Matcha-TTS with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Card: plainer wording
Browse files- Wording: plainer words for a few other things.
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
|
| 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 |
|