Text-to-Speech
Transformers
ONNX
GGUF
Chinese
English
voice-dialogue
speech-recognition
large-language-model
asr
tts
llm
chinese
english
real-time
conversational
Instructions to use MoYoYoTech/VoiceDialogue with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use MoYoYoTech/VoiceDialogue with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-to-speech", model="MoYoYoTech/VoiceDialogue") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("MoYoYoTech/VoiceDialogue", dtype="auto") - llama-cpp-python
How to use MoYoYoTech/VoiceDialogue with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="MoYoYoTech/VoiceDialogue", filename="assets/models/llm/qwen/Qwen3-8B-Q6_K.gguf", )
llm.create_chat_completion( messages = "\"The answer to the universe is 42\"" )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use MoYoYoTech/VoiceDialogue with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf MoYoYoTech/VoiceDialogue:Q6_K # Run inference directly in the terminal: llama-cli -hf MoYoYoTech/VoiceDialogue:Q6_K
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf MoYoYoTech/VoiceDialogue:Q6_K # Run inference directly in the terminal: llama-cli -hf MoYoYoTech/VoiceDialogue:Q6_K
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf MoYoYoTech/VoiceDialogue:Q6_K # Run inference directly in the terminal: ./llama-cli -hf MoYoYoTech/VoiceDialogue:Q6_K
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf MoYoYoTech/VoiceDialogue:Q6_K # Run inference directly in the terminal: ./build/bin/llama-cli -hf MoYoYoTech/VoiceDialogue:Q6_K
Use Docker
docker model run hf.co/MoYoYoTech/VoiceDialogue:Q6_K
- LM Studio
- Jan
- Ollama
How to use MoYoYoTech/VoiceDialogue with Ollama:
ollama run hf.co/MoYoYoTech/VoiceDialogue:Q6_K
- Unsloth Studio
How to use MoYoYoTech/VoiceDialogue with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for MoYoYoTech/VoiceDialogue to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for MoYoYoTech/VoiceDialogue to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for MoYoYoTech/VoiceDialogue to start chatting
- Pi
How to use MoYoYoTech/VoiceDialogue with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf MoYoYoTech/VoiceDialogue:Q6_K
Configure the model in Pi
# Install Pi: npm install -g @mariozechner/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "llama-cpp": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "MoYoYoTech/VoiceDialogue:Q6_K" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use MoYoYoTech/VoiceDialogue with Hermes Agent:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf MoYoYoTech/VoiceDialogue:Q6_K
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default MoYoYoTech/VoiceDialogue:Q6_K
Run Hermes
hermes
- Docker Model Runner
How to use MoYoYoTech/VoiceDialogue with Docker Model Runner:
docker model run hf.co/MoYoYoTech/VoiceDialogue:Q6_K
- Lemonade
How to use MoYoYoTech/VoiceDialogue with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull MoYoYoTech/VoiceDialogue:Q6_K
Run and chat with the model
lemonade run user.VoiceDialogue-Q6_K
List all available models
lemonade list
Xin Zhang commited on
Commit ·
797cd52
1
Parent(s): c531bfc
[fix]: voice selection bugfix.
Browse files
frontend/src/views/Welcome/Components/PromptText.vue
CHANGED
|
@@ -140,6 +140,7 @@ watch(() => props.open, (newOpen) => {
|
|
| 140 |
v-model:open="props.open"
|
| 141 |
:title="null"
|
| 142 |
:mask-closable="false"
|
|
|
|
| 143 |
centered
|
| 144 |
@update:open="(val: boolean) => emit('update:open', val)"
|
| 145 |
>
|
|
@@ -170,7 +171,7 @@ watch(() => props.open, (newOpen) => {
|
|
| 170 |
allow-clear
|
| 171 |
class="prompt-textarea"
|
| 172 |
/>
|
| 173 |
-
<a-button key="
|
| 174 |
</div>
|
| 175 |
<div v-if="languageSegment == 'zh'" class="prompt-item">
|
| 176 |
<a-textarea
|
|
@@ -182,7 +183,7 @@ watch(() => props.open, (newOpen) => {
|
|
| 182 |
allow-clear
|
| 183 |
class="prompt-textarea"
|
| 184 |
/>
|
| 185 |
-
<a-button key="
|
| 186 |
</div>
|
| 187 |
</div>
|
| 188 |
</a-modal>
|
|
@@ -205,7 +206,7 @@ watch(() => props.open, (newOpen) => {
|
|
| 205 |
}
|
| 206 |
|
| 207 |
.prompt-content {
|
| 208 |
-
margin-top:
|
| 209 |
|
| 210 |
.prompt-title {
|
| 211 |
margin-bottom: 24px;
|
|
|
|
| 140 |
v-model:open="props.open"
|
| 141 |
:title="null"
|
| 142 |
:mask-closable="false"
|
| 143 |
+
:closable="false"
|
| 144 |
centered
|
| 145 |
@update:open="(val: boolean) => emit('update:open', val)"
|
| 146 |
>
|
|
|
|
| 171 |
allow-clear
|
| 172 |
class="prompt-textarea"
|
| 173 |
/>
|
| 174 |
+
<a-button size="small" key="reset-en" @click="handleResetPrompt('en')" style="margin-top: 16px;">Reset</a-button>
|
| 175 |
</div>
|
| 176 |
<div v-if="languageSegment == 'zh'" class="prompt-item">
|
| 177 |
<a-textarea
|
|
|
|
| 183 |
allow-clear
|
| 184 |
class="prompt-textarea"
|
| 185 |
/>
|
| 186 |
+
<a-button size="small" key="reset-zh" @click="handleResetPrompt('zh')" style="margin-top: 16px;">Reset</a-button>
|
| 187 |
</div>
|
| 188 |
</div>
|
| 189 |
</a-modal>
|
|
|
|
| 206 |
}
|
| 207 |
|
| 208 |
.prompt-content {
|
| 209 |
+
margin-top: 16px;
|
| 210 |
|
| 211 |
.prompt-title {
|
| 212 |
margin-bottom: 24px;
|
frontend/src/views/Welcome/index.vue
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
|
| 3 |
import router from "@/router.ts";
|
| 4 |
import { useSettingsStore } from "@/stores/config.ts";
|
| 5 |
-
import { onMounted, onUnmounted, ref, reactive, computed, h } from "vue";
|
| 6 |
import { Modal } from 'ant-design-vue';
|
| 7 |
import { SoundTwoTone, SoundOutlined } from "@ant-design/icons-vue";
|
| 8 |
import axios from "axios";
|
|
@@ -67,6 +67,8 @@ const modalLoading = ref<boolean>(false);
|
|
| 67 |
|
| 68 |
const handleVoiceModalCancel = () => {
|
| 69 |
voiceModelOpen.value = false;
|
|
|
|
|
|
|
| 70 |
};
|
| 71 |
|
| 72 |
const handleVoiceModalSubmit = async () => {
|
|
@@ -153,6 +155,18 @@ const filteredRoles = computed(() => {
|
|
| 153 |
return roles.filter(ro => ro['is_chinese_voice'] == is_chinese);
|
| 154 |
});
|
| 155 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 156 |
|
| 157 |
const fetchTTSRoles = async () => {
|
| 158 |
try {
|
|
@@ -318,11 +332,11 @@ const isPlaying = (id: string) => {
|
|
| 318 |
<div class="custom-popover-item" @click="togglePopover('prompt')">Prompt调试</div>
|
| 319 |
</div>
|
| 320 |
</template>
|
| 321 |
-
<img :src="setting" alt="item actions" style="width: 28px; height: 28px; margin-right:24px;margin-
|
| 322 |
</a-popover>
|
| 323 |
</div>
|
| 324 |
|
| 325 |
-
<a-modal v-model:open="voiceModelOpen" :title="null" :mask-closable="false" centered>
|
| 326 |
<template #footer>
|
| 327 |
<a-button key="back" @click="handleVoiceModalCancel">Cancel</a-button>
|
| 328 |
<a-button key="submit" type="primary" :loading="modalLoading" @click="handleVoiceModalSubmit">Submit</a-button>
|
|
@@ -385,8 +399,8 @@ const isPlaying = (id: string) => {
|
|
| 385 |
<style lang="scss" scoped>
|
| 386 |
|
| 387 |
.languages {
|
| 388 |
-
margin-top:
|
| 389 |
-
margin-bottom:
|
| 390 |
|
| 391 |
p {
|
| 392 |
font-size: 16px;
|
|
|
|
| 2 |
|
| 3 |
import router from "@/router.ts";
|
| 4 |
import { useSettingsStore } from "@/stores/config.ts";
|
| 5 |
+
import { onMounted, onUnmounted, ref, reactive, computed, watch, h } from "vue";
|
| 6 |
import { Modal } from 'ant-design-vue';
|
| 7 |
import { SoundTwoTone, SoundOutlined } from "@ant-design/icons-vue";
|
| 8 |
import axios from "axios";
|
|
|
|
| 67 |
|
| 68 |
const handleVoiceModalCancel = () => {
|
| 69 |
voiceModelOpen.value = false;
|
| 70 |
+
role.value = settingsStore.$state.role;
|
| 71 |
+
language.value = settingsStore.$state.language;
|
| 72 |
};
|
| 73 |
|
| 74 |
const handleVoiceModalSubmit = async () => {
|
|
|
|
| 155 |
return roles.filter(ro => ro['is_chinese_voice'] == is_chinese);
|
| 156 |
});
|
| 157 |
|
| 158 |
+
watch(
|
| 159 |
+
() => language.value,
|
| 160 |
+
(newLang) => {
|
| 161 |
+
// 语言切换后,自动选中第一个可用角色
|
| 162 |
+
if (filteredRoles.value.length > 0) {
|
| 163 |
+
role.value = filteredRoles.value[0]['id'];
|
| 164 |
+
} else {
|
| 165 |
+
role.value = "";
|
| 166 |
+
}
|
| 167 |
+
}
|
| 168 |
+
);
|
| 169 |
+
|
| 170 |
|
| 171 |
const fetchTTSRoles = async () => {
|
| 172 |
try {
|
|
|
|
| 332 |
<div class="custom-popover-item" @click="togglePopover('prompt')">Prompt调试</div>
|
| 333 |
</div>
|
| 334 |
</template>
|
| 335 |
+
<img :src="setting" alt="item actions" style="width: 28px; height: 28px; margin-right:24px;margin-top: 16px;">
|
| 336 |
</a-popover>
|
| 337 |
</div>
|
| 338 |
|
| 339 |
+
<a-modal v-model:open="voiceModelOpen" :title="null" :mask-closable="false" :closable="false" centered>
|
| 340 |
<template #footer>
|
| 341 |
<a-button key="back" @click="handleVoiceModalCancel">Cancel</a-button>
|
| 342 |
<a-button key="submit" type="primary" :loading="modalLoading" @click="handleVoiceModalSubmit">Submit</a-button>
|
|
|
|
| 399 |
<style lang="scss" scoped>
|
| 400 |
|
| 401 |
.languages {
|
| 402 |
+
margin-top: 24px;
|
| 403 |
+
margin-bottom: 24px;
|
| 404 |
|
| 405 |
p {
|
| 406 |
font-size: 16px;
|