Card: point to v2
Browse files
README.md
CHANGED
|
@@ -10,6 +10,8 @@ datasets: [machinekind/polish-synthetic-speech-voxcpm2]
|
|
| 10 |
|
| 11 |
# Matcha-TTS-PL-Edge — Polish TTS for CPUs: fp32 · int8 · streaming
|
| 12 |
|
|
|
|
|
|
|
| 13 |
The voices of [Matcha-TTS-PL](https://huggingface.co/machinekind/Matcha-TTS-PL) for Raspberry Pi / Jetson-class CPUs, in one
|
| 14 |
repo: **fp32 and pre-quantised int8** ONNX graphs, a **15× smaller vocoder**, and **streaming** (first audio in ~80 ms on one
|
| 15 |
Pi-class core). One inference file (`tts.py`, onnxruntime + numpy) does whole sentences and streaming.
|
|
|
|
| 10 |
|
| 11 |
# Matcha-TTS-PL-Edge — Polish TTS for CPUs: fp32 · int8 · streaming
|
| 12 |
|
| 13 |
+
> **Newer version:** [Matcha-TTS-PL-Edge-v2](https://huggingface.co/machinekind/Matcha-TTS-PL-Edge-v2).
|
| 14 |
+
|
| 15 |
The voices of [Matcha-TTS-PL](https://huggingface.co/machinekind/Matcha-TTS-PL) for Raspberry Pi / Jetson-class CPUs, in one
|
| 16 |
repo: **fp32 and pre-quantised int8** ONNX graphs, a **15× smaller vocoder**, and **streaming** (first audio in ~80 ms on one
|
| 17 |
Pi-class core). One inference file (`tts.py`, onnxruntime + numpy) does whole sentences and streaming.
|