Jarbas commited on
Commit
9cf004f
·
verified ·
1 Parent(s): 81e80eb

docs: model card

Browse files
Files changed (1) hide show
  1. README.md +21 -0
README.md ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ pipeline_tag: text-to-speech
4
+ library_name: phoonnx
5
+ tags: [phoonnx, optispeech, tts]
6
+ ---
7
+ # phoonnx-optispeech
8
+ OptiSpeech voices for [phoonnx](https://github.com/TigreGotico/phoonnx) — non-autoregressive (FastSpeech2-style)
9
+ acoustic + GAN vocoder, single ONNX (waveform out). One voice per subfolder
10
+ (`model.onnx` + native `config.json`). Mirror of
11
+ [mush42/optispeech](https://huggingface.co/mush42/optispeech), en-US, 24 kHz.
12
+ Part of the [phoonnx community mirror](https://huggingface.co/collections/OpenVoiceOS/phoonnx-community-mirror-6a2204d302e0e7497870cd68).
13
+
14
+ | voice | acoustic | speaker |
15
+ |---|---|---|
16
+ | `mush42__optispeech-lightspeech-en-us-emily` | LightSpeech | emily |
17
+ | `mush42__optispeech-lightspeech-en-us-mike` | LightSpeech | mike |
18
+ | `mush42__optispeech-convnext-en-us-emily` | ConvNeXt-TTS | emily |
19
+
20
+ The native `config.json` is generated from OptiSpeech's embedded ONNX metadata.
21
+ See [docs/optispeech.md](https://github.com/TigreGotico/phoonnx/blob/dev/docs/optispeech.md).