From 1fccc97fb99c2374a92346080cc8ce3152d44f57 Mon Sep 17 00:00:00 2001
From: Vaibhav Srivastav <vaibhavs10@gmail.com>
Date: Wed, 14 Aug 2024 11:54:42 +0200
Subject: [PATCH] Minor doc fix.

---
 README.md | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/README.md b/README.md
index 75fe28e..5dff234 100644
--- a/README.md
+++ b/README.md
@@ -19,8 +19,8 @@
 ### Structure
 This repository implements a speech-to-speech cascaded pipeline with consecutive parts:
 1. **Voice Activity Detection (VAD)**: [silero VAD v5](https://github.com/snakers4/silero-vad)
-2. **Speech to Text (STT)**: Whisper models (including distilled versions)
-3. **Language Model (LM)**: Any instruct model available on the [Hugging Face Hub](https://huggingface.co/models)! 🤗
+2. **Speech to Text (STT)**: Whisper checkpoints (including [distilled versions](https://huggingface.co/distil-whisper))
+3. **Language Model (LM)**: Any instruct model available on the [Hugging Face Hub](https://huggingface.co/models?pipeline_tag=text-generation&sort=trending)! 🤗
 4. **Text to Speech (TTS)**: [Parler-TTS](https://github.com/huggingface/parler-tts)
 
 ### Modularity
@@ -70,6 +70,8 @@ python s2s_pipeline.py --recv_host localhost --send_host localhost
 python listen_and_play.py --host localhost
 ```
 
+You can pass `--device mps` to run it locally on a Mac.
+
 ## Command-line Usage
 
 ### Model Parameters
-- 
GitLab