From c3d7ab4adce98e8f46edb1a31374f2f64d72f51c Mon Sep 17 00:00:00 2001 From: Arcitec <38923130+Arcitec@users.noreply.github.com> Date: Wed, 10 Sep 2025 19:14:46 +0200 Subject: [PATCH] docs: Add usage note regarding random sampling --- README.md | 4 ++++ docs/README_zh.md | 2 +- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 26228f9..4e68c71 100644 --- a/README.md +++ b/README.md @@ -314,6 +314,10 @@ tts.infer(spk_audio_prompt='examples/voice_07.wav', text=text, output_path="gen. during inference; the default is `False`, and setting it to `True` enables randomness: +> [!NOTE] +> Enabling random sampling will reduce the voice cloning fidelity of the speech +> synthesis. + ```python from indextts.infer_v2 import IndexTTS2 tts = IndexTTS2(cfg_path="checkpoints/config.yaml", model_dir="checkpoints", use_fp16=False, use_cuda_kernel=False, use_deepspeed=False) diff --git a/docs/README_zh.md b/docs/README_zh.md index 8af79bc..3b8a205 100644 --- a/docs/README_zh.md +++ b/docs/README_zh.md @@ -261,9 +261,9 @@ tts.infer(spk_audio_prompt='examples/voice_07.wav', text=text, output_path="gen. ``` 4. 可直接指定8维情感向量 `[高兴, 愤怒, 悲伤, 害怕, 厌恶, 忧郁, 惊讶, 平静]`,可用`use_random`开启随机情感采样(默认False): + > [!NOTE] > 开启随机采样会降低音色的还原度。 -> ```python from indextts.infer_v2 import IndexTTS2