Update README.md

README.md

@@ -10,46 +10,79 @@ tags:
 - gguf-my-repo
 ---
 
-# isaiahbjork/orpheus-3b-0.1-ft-Q4_K_M-GGUF
-This model was converted to GGUF format from [`canopylabs/orpheus-3b-0.1-ft`](https://huggingface.co/canopylabs/orpheus-3b-0.1-ft) using llama.cpp via the ggml.ai's [GGUF-my-repo](https://huggingface.co/spaces/ggml-org/gguf-my-repo) space.
-Refer to the [original model card](https://huggingface.co/canopylabs/orpheus-3b-0.1-ft) for more details on the model.
+# Orpheus-TTS-Local
 
-## Use with llama.cpp
-Install llama.cpp through brew (works on Mac and Linux)
+A lightweight client for running [Orpheus TTS](https://huggingface.co/canopylabs/orpheus-3b-0.1-ft) locally using LM Studio API.
 
-```bash
-brew install llama.cpp
+{Github Repo](https://github.com/isaiahbjork/orpheus-tts-local)
 
-```
-Invoke the llama.cpp server or the CLI.
+## Features
 
-### CLI:
-```bash
-llama-cli --hf-repo isaiahbjork/orpheus-3b-0.1-ft-Q4_K_M-GGUF --hf-file orpheus-3b-0.1-ft-q4_k_m.gguf -p "The meaning to life and the universe is"
-```
+- 🎧 High-quality Text-to-Speech using the Orpheus TTS model
+- 💻 Completely local - no cloud API keys needed
+- 🔊 Multiple voice options (tara, leah, jess, leo, dan, mia, zac, zoe)
+- 💾 Save audio to WAV files
 
-### Server:
-```bash
-llama-server --hf-repo isaiahbjork/orpheus-3b-0.1-ft-Q4_K_M-GGUF --hf-file orpheus-3b-0.1-ft-q4_k_m.gguf -c 2048
-```
+## Quick Setup
 
-Note: You can also use this checkpoint directly through the [usage steps](https://github.com/ggerganov/llama.cpp?tab=readme-ov-file#usage) listed in the Llama.cpp repo as well.
+1. Install [LM Studio](https://lmstudio.ai/) 
+2. Install the [Orpheus TTS model (orpheus-3b-0.1-ft-q4_k_m.gguf)](https://huggingface.co/isaiahbjork/orpheus-3b-0.1-ft-Q4_K_M-GGUF) in LM Studio
+3. Load the Orpheus model in LM Studio
+4. Start the local server in LM Studio (default: http://127.0.0.1:1234)
+5. Install dependencies:
+   ```
+   python3 -m venv venv
+   source venv/bin/activate
+   pip install -r requirements.txt
+   ```
+6. Run the script:
+   ```
+   python gguf_orpheus.py --text "Hello, this is a test" --voice tara
+   ```
 
-Step 1: Clone llama.cpp from GitHub.
-```
-git clone https://github.com/ggerganov/llama.cpp
-```
+## Usage
 
-Step 2: Move into the llama.cpp folder and build it with `LLAMA_CURL=1` flag along with other hardware-specific flags (for ex: LLAMA_CUDA=1 for Nvidia GPUs on Linux).
 ```
-cd llama.cpp && LLAMA_CURL=1 make
+python gguf_orpheus.py --text "Your text here" --voice tara --output "output.wav"
 ```
 
-Step 3: Run inference through the main binary.
-```
-./llama-cli --hf-repo isaiahbjork/orpheus-3b-0.1-ft-Q4_K_M-GGUF --hf-file orpheus-3b-0.1-ft-q4_k_m.gguf -p "The meaning to life and the universe is"
-```
-or 
-```
-./llama-server --hf-repo isaiahbjork/orpheus-3b-0.1-ft-Q4_K_M-GGUF --hf-file orpheus-3b-0.1-ft-q4_k_m.gguf -c 2048
+### Options
+
+- `--text`: The text to convert to speech
+- `--voice`: The voice to use (default: tara)
+- `--output`: Output WAV file path (default: auto-generated filename)
+- `--list-voices`: Show available voices
+- `--temperature`: Temperature for generation (default: 0.6)
+- `--top_p`: Top-p sampling parameter (default: 0.9)
+- `--repetition_penalty`: Repetition penalty (default: 1.1)
+
+## Available Voices
+
+- tara - Best overall voice for general use (default)
+- leah
+- jess
+- leo
+- dan
+- mia
+- zac
+- zoe
+
+## Emotion
+You can add emotion to the speech by adding the following tags:
+```xml
+<giggle>
+<laugh>
+<chuckle>
+<sigh>
+<cough>
+<sniffle>
+<groan>
+<yawn>
+<gasp>
 ```
+
+## License
+
+Apache 2.0
+
+