Open-Source Frontier Voice AI
Python
docs: minor wording fixes in contributing and VibeVoice guides
dhunganapramod917f57f82ee75
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.mdindex 433a8c0..372d08c 100644--- a/CONTRIBUTING.md+++ b/CONTRIBUTING.md@@ -15,7 +15,7 @@ Our core principles are **code minimalism**, **high readability**, and **functio- **Over-Engineering**We will reject unnecessary encapsulation, excessive abstraction, or complex architectural refactoring.- Please remember this is research-purposed code, not a commercial enterprise project.+ Please remember this is research-oriented code, not a commercial enterprise project.- **Style Tweaks**PRs solely for formatting, beautification, or non-functional style adjustments will be rejected.diff --git a/docs/vibevoice-asr.md b/docs/vibevoice-asr.mdindex 823875e..5e65944 100644--- a/docs/vibevoice-asr.md+++ b/docs/vibevoice-asr.md@@ -52,7 +52,7 @@ https://github.com/user-attachments/assets/acde5602-dc17-4314-9e3b-c630bc84aefa## Installation-We recommend to use NVIDIA Deep Learning Container to manage the CUDA environment.+We recommend using NVIDIA Deep Learning Container to manage the CUDA environment.1. Launch docker```bashdiff --git a/docs/vibevoice-realtime-0.5b.md b/docs/vibevoice-realtime-0.5b.mdindex edfd099..6ca2deb 100644--- a/docs/vibevoice-realtime-0.5b.md+++ b/docs/vibevoice-realtime-0.5b.md@@ -79,7 +79,7 @@ The model achieves satisfactory performance on short-sentence benchmarks, while## Installation-We recommend to use NVIDIA Deep Learning Container to manage the CUDA environment.+We recommend using NVIDIA Deep Learning Container to manage the CUDA environment.1. Launch docker```bash@@ -105,7 +105,7 @@ pip install -e .[streamingtts]### Usage 1: Launch real-time websocket demo-Note: NVIDIA T4 / Mac M4 Pro achieve realtime in our tests; other devices with weaker inference capability may require further testing and speed optimizations.+Note: NVIDIA T4 / Mac M4 Pro achieve real-time performance in our tests; other devices with weaker inference capability may require further testing and speed optimizations.Due to network latency, the time when audio playback is heard may exceed the ~300 ms first speech chunk generation latency.```bashdiff --git a/docs/vibevoice-tts.md b/docs/vibevoice-tts.mdindex b8853e2..a3a5f77 100644--- a/docs/vibevoice-tts.md+++ b/docs/vibevoice-tts.md@@ -102,7 +102,7 @@ We observed users may encounter occasional instability when synthesizing Chinese- Using English punctuation even for Chinese text, preferably only commas and periods.- Using the Large model variant, which is considerably more stable.-- If you found the generated voice speak too fast. Please try to chunk your text with multiple speaker turns with same speaker label.+- If you find that the generated voice speaks too fast, try chunking your text into multiple turns with the same speaker label.We'd like to thank [PsiPi](https://huggingface.co/PsiPi) for sharing an interesting way for emotion control. Details can be found via [discussion12](https://huggingface.co/microsoft/VibeVoice-1.5B/discussions/12).