feat: update README

README.md

@@ -2,6 +2,8 @@
 license: apache-2.0
 language:
 - en
+tags:
+  - pretrained
 ---
 
 MetaVoice-1B is a 1.2B parameter base model trained on 100K hours of speech for TTS (text-to-speech). It has been built with the following priorities:
@@ -13,38 +15,8 @@ MetaVoice-1B is a 1.2B parameter base model trained on 100K hours of speech for
 
 We’re releasing MetaVoice-1B under the Apache 2.0 license, *it can be used without restrictions*.
 
-## Installation
-```bash
-# install ffmpeg
-wget https://johnvansickle.com/ffmpeg/builds/ffmpeg-git-amd64-static.tar.xz
-wget https://johnvansickle.com/ffmpeg/builds/ffmpeg-git-amd64-static.tar.xz.md5
-md5sum -c ffmpeg-git-amd64-static.tar.xz.md5
-tar xvf ffmpeg-git-amd64-static.tar.xz
-sudo mv ffmpeg-git-*-static/ffprobe ffmpeg-git-*-static/ffmpeg /usr/local/bin/
-rm -rf ffmpeg-git-*
-
-pip install -r requirements.txt
-pip install -e .
-```
-
-## Download
-```
-wget https://cdn.themetavoice.xyz/metavoice-1B-v0.1.tar
-tar -xvf metavoice-1B-v0.1.tar
-```
-
 ## Usage
-1. [Download it](https://cdn.themetavoice.xyz/metavoice-1B-v0.1.tar) and use it anywhere (including locally) with our [reference implementation](/fam/llm/sample.py),
-```bash
-python fam/llm/sample.py --model_dir=<PATH_TO_MODEL_DIR> --spk_cond_path=<PATH_TO_TARGET_AUDIO>
-```
-
-2. Deploy it on any cloud (AWS/GCP/Azure), using our [inference server](/fam/llm/serving.py)
-```bash
-python fam/llm/serving.py --model_dir=<PATH_TO_MODEL_DIR>
-```
-
-3. Use it on HuggingFace
+See [Github](https://github.com/metavoiceio/metavoice-src) for the latest usage instructions.
 
 ## Soon
 - Long form TTS
@@ -66,6 +38,3 @@ We predict EnCodec tokens from text, and speaker information. This is then diffu
 The model supports: 
 1. KV-caching via Flash Decoding 
 2. Batching (including texts of different lengths)
-
-## Contribute
-- See all [active issues](https://github.com/themetavoicexyz/issues)!