vinhnx90 commited on
Commit
142761b
·
verified ·
1 Parent(s): 2b1734a

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +45 -45
README.md CHANGED
@@ -57,50 +57,50 @@ This section provides a step-by-step guide to running the `VT-Orpheus-3B-TTS-Cey
57
  ### Setup Steps
58
 
59
  1. **Install LM Studio**
60
- - Download and install LM Studio from [lmstudio.ai](https://lmstudio.ai/)
61
- - Launch LM Studio
62
 
63
  2. **Load the GGUF model**
64
- - In LM Studio, click "Add Model"
65
- - Select the `VT-Orpheus-3B-TTS-Ceylia.Q4_K_M.gguf` file from your computer
66
- - Once added, click on the model to load it
67
 
68
  3. **Start the local server**
69
- - Go to the "Local Server" tab in LM Studio
70
- - Click "Start Server" to launch the local API server (default address is `http://127.0.0.1:1234`)
71
 
72
  4. **Clone orpheus-tts-local repository**
73
 
74
- ```bash
75
- git clone https://github.com/isaiahbjork/orpheus-tts-local.git
76
- cd orpheus-tts-local
77
- ```
78
 
79
  5. **Install dependencies**
80
 
81
- ```bash
82
- python -m venv venv
83
- source venv/bin/activate # On Windows: venv\Scripts\activate
84
- pip install -r requirements.txt
85
- ```
86
 
87
  5.1 **Edit gguf_orpheus.py to include new ceylia voice**
88
 
89
  Open `gguf_orpheus.py` file in ./orpheus-tts-local directory, find the line of `AVAILABLE_VOICES` and `DEFAULT_VOICE` and edit to include ceylia voice, default is `tara`.
90
 
91
- ```python
92
- # Available voices based on the Orpheus-TTS repository
93
- AVAILABLE_VOICES = ["tara", "leah", "jess", "leo", "dan", "mia", "zac", "zoe", "ceylia"]
94
- DEFAULT_VOICE = "ceylia"
95
- ```
96
 
97
  Save the file `gguf_orpheus.py`.
98
 
99
  6. **Run the model**
100
 
101
- ```bash
102
- python gguf_orpheus.py --text "Hi! I'm Ceylia. <laugh> This is so exciting! <giggle>" --voice ceylia --output output.wav
103
- ```
104
 
105
  ### Available Parameters
106
 
@@ -123,39 +123,39 @@ Save the file `gguf_orpheus.py`.
123
 
124
  1. **Clone and build llama.cpp**
125
 
126
- ```bash
127
- git clone https://github.com/ggerganov/llama.cpp
128
- cd llama.cpp
129
- cmake -B build
130
- cmake --build build --config Release
131
- ```
132
 
133
  2. **Start the server**
134
 
135
- ```bash
136
- ./llama-server -m /path/to/VT-Orpheus-3B-TTS-Ceylia.Q4_K_M.gguf --port 8080
137
- ```
138
 
139
  3. **Clone orpheus-tts-local repository**
140
 
141
- ```bash
142
- git clone https://github.com/isaiahbjork/orpheus-tts-local.git
143
- cd orpheus-tts-local
144
- ```
145
 
146
  4. **Install dependencies**
147
 
148
- ```bash
149
- python -m venv venv
150
- source venv/bin/activate # On Windows: venv\Scripts\activate
151
- pip install -r requirements.txt
152
- ```
153
 
154
  5. **Run the model with custom API URL**
155
 
156
- ```bash
157
- python gguf_orpheus.py --text "Hi! I'm Ceylia. <laugh> Let's play! <sniffle> This is so exciting! <giggle>" --voice ceylia --output output.wav --api_url http://localhost:8080/v1
158
- ```
159
 
160
  ## Emotion Tags
161
 
 
57
  ### Setup Steps
58
 
59
  1. **Install LM Studio**
60
+ - Download and install LM Studio from [lmstudio.ai](https://lmstudio.ai/)
61
+ - Launch LM Studio
62
 
63
  2. **Load the GGUF model**
64
+ - In LM Studio, click "Add Model"
65
+ - Select the `VT-Orpheus-3B-TTS-Ceylia.Q4_K_M.gguf` file from your computer
66
+ - Once added, click on the model to load it
67
 
68
  3. **Start the local server**
69
+ - Go to the "Local Server" tab in LM Studio
70
+ - Click "Start Server" to launch the local API server (default address is `http://127.0.0.1:1234`)
71
 
72
  4. **Clone orpheus-tts-local repository**
73
 
74
+ ```bash
75
+ git clone https://github.com/isaiahbjork/orpheus-tts-local.git
76
+ cd orpheus-tts-local
77
+ ```
78
 
79
  5. **Install dependencies**
80
 
81
+ ```bash
82
+ python -m venv venv
83
+ source venv/bin/activate # On Windows: venv\Scripts\activate
84
+ pip install -r requirements.txt
85
+ ```
86
 
87
  5.1 **Edit gguf_orpheus.py to include new ceylia voice**
88
 
89
  Open `gguf_orpheus.py` file in ./orpheus-tts-local directory, find the line of `AVAILABLE_VOICES` and `DEFAULT_VOICE` and edit to include ceylia voice, default is `tara`.
90
 
91
+ ```python
92
+ # Available voices based on the Orpheus-TTS repository
93
+ AVAILABLE_VOICES = ["tara", "leah", "jess", "leo", "dan", "mia", "zac", "zoe", "ceylia"]
94
+ DEFAULT_VOICE = "ceylia"
95
+ ```
96
 
97
  Save the file `gguf_orpheus.py`.
98
 
99
  6. **Run the model**
100
 
101
+ ```bash
102
+ python gguf_orpheus.py --text "Hi! I'm Ceylia. <laugh> This is so exciting! <giggle>" --voice ceylia --output output.wav
103
+ ```
104
 
105
  ### Available Parameters
106
 
 
123
 
124
  1. **Clone and build llama.cpp**
125
 
126
+ ```bash
127
+ git clone https://github.com/ggerganov/llama.cpp
128
+ cd llama.cpp
129
+ cmake -B build
130
+ cmake --build build --config Release
131
+ ```
132
 
133
  2. **Start the server**
134
 
135
+ ```bash
136
+ ./llama-server -m /path/to/VT-Orpheus-3B-TTS-Ceylia.Q4_K_M.gguf --port 8080
137
+ ```
138
 
139
  3. **Clone orpheus-tts-local repository**
140
 
141
+ ```bash
142
+ git clone https://github.com/isaiahbjork/orpheus-tts-local.git
143
+ cd orpheus-tts-local
144
+ ```
145
 
146
  4. **Install dependencies**
147
 
148
+ ```bash
149
+ python -m venv venv
150
+ source venv/bin/activate # On Windows: venv\Scripts\activate
151
+ pip install -r requirements.txt
152
+ ```
153
 
154
  5. **Run the model with custom API URL**
155
 
156
+ ```bash
157
+ python gguf_orpheus.py --text "Hi! I'm Ceylia. <laugh> Let's play! <sniffle> This is so exciting! <giggle>" --voice ceylia --output output.wav --api_url http://localhost:8080/v1
158
+ ```
159
 
160
  ## Emotion Tags
161