Add X-VC voice conversion mode

2026-09-09 16:14:10 +02:00
parent 17f1a08d7d
commit 87a2ae5704
15 changed files with 544 additions and 28 deletions
@@ -0,0 +1,24 @@
+# X-VC voice conversion on Athena
+
+Isolated quality gate for `chenxie95/X-VC`, using the official inference path
+from commit `49df8c591eafc48b096e466d96f9839f9c0dd739`. The UI is adapted from the
+public Hugging Face Space at commit
+`d761cd6421e85376b2656dfefd8471d7f35a42be` and runs locally without
+ZeroGPU.
+
+- Private URL: `http://192.168.1.212:8009`
+- Source clip: speech content and timing to preserve
+- Reference clip: target speaker identity
+- Output: 16 kHz PCM WAV
+- GPU: RTX 5080 only
+- Persistent cache: `/data/voice/xvc/huggingface`
+- Code and model license: MIT
+
+The semantic tokenizer documents Chinese and English. German is therefore a
+quality gate, not an assumed supported language. Keep OmniVoice installed: it
+does text-to-speech cloning, while X-VC tests true audio-to-audio conversion.
+
+Technical acceptance on 9 September 2026 used the repository's source and
+target examples: 5.20 seconds were converted in 1.07 seconds (RTF 0.21). The
+result was valid mono PCM WAV at 16 kHz, and the loaded process occupied about
+2.9 GiB on the RTX 5080. German listening quality remains open.