Instructions to use MoYoYoTech/Translator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use MoYoYoTech/Translator with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="MoYoYoTech/Translator", filename="moyoyo_asr_models/qwen2.5-1.5b-instruct-q5_0.gguf", )
llm.create_chat_completion( messages = "No input example has been defined for this model task." )
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use MoYoYoTech/Translator with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf MoYoYoTech/Translator:Q5_0 # Run inference directly in the terminal: llama-cli -hf MoYoYoTech/Translator:Q5_0
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf MoYoYoTech/Translator:Q5_0 # Run inference directly in the terminal: llama-cli -hf MoYoYoTech/Translator:Q5_0
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/Translator:Q5_0 # Run inference directly in the terminal: ./llama-cli -hf MoYoYoTech/Translator:Q5_0
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/Translator:Q5_0 # Run inference directly in the terminal: ./build/bin/llama-cli -hf MoYoYoTech/Translator:Q5_0
Use Docker
docker model run hf.co/MoYoYoTech/Translator:Q5_0
- LM Studio
- Jan
- Ollama
How to use MoYoYoTech/Translator with Ollama:
ollama run hf.co/MoYoYoTech/Translator:Q5_0
- Unsloth Studio
How to use MoYoYoTech/Translator 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/Translator 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/Translator to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for MoYoYoTech/Translator to start chatting
- Pi
How to use MoYoYoTech/Translator with Pi:
Start the llama.cpp server
# Install llama.cpp: brew install llama.cpp # Start a local OpenAI-compatible server: llama-server -hf MoYoYoTech/Translator:Q5_0
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/Translator:Q5_0" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent new
How to use MoYoYoTech/Translator 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/Translator:Q5_0
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/Translator:Q5_0
Run Hermes
hermes
- Docker Model Runner
How to use MoYoYoTech/Translator with Docker Model Runner:
docker model run hf.co/MoYoYoTech/Translator:Q5_0
- Lemonade
How to use MoYoYoTech/Translator with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull MoYoYoTech/Translator:Q5_0
Run and chat with the model
lemonade run user.Translator-Q5_0
List all available models
lemonade list
daihui.zhang commited on
Commit ·
ab22d1a
1
Parent(s): 0b0ef2f
fix error handle in main
Browse files- main.py +7 -5
- transcribe/whisper_llm_serve.py +21 -12
main.py
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
-
from fastapi import FastAPI, WebSocket
|
| 2 |
from urllib.parse import urlparse, parse_qsl
|
| 3 |
from transcribe.whisper_llm_serve import PyWhiperCppServe
|
| 4 |
from uuid import uuid1
|
|
@@ -68,10 +68,12 @@ async def translate(websocket: WebSocket):
|
|
| 68 |
client.set_lang(from_lang, to_lang)
|
| 69 |
logger.info(f"Source lange: {from_lang} -> Dst lange: {to_lang}")
|
| 70 |
await websocket.accept()
|
| 71 |
-
|
| 72 |
-
|
| 73 |
-
|
| 74 |
-
|
|
|
|
|
|
|
| 75 |
|
| 76 |
if __name__ == '__main__':
|
| 77 |
freeze_support()
|
|
|
|
| 1 |
+
from fastapi import FastAPI, WebSocket, WebSocketDisconnect
|
| 2 |
from urllib.parse import urlparse, parse_qsl
|
| 3 |
from transcribe.whisper_llm_serve import PyWhiperCppServe
|
| 4 |
from uuid import uuid1
|
|
|
|
| 68 |
client.set_lang(from_lang, to_lang)
|
| 69 |
logger.info(f"Source lange: {from_lang} -> Dst lange: {to_lang}")
|
| 70 |
await websocket.accept()
|
| 71 |
+
try:
|
| 72 |
+
while True:
|
| 73 |
+
frame_data = await get_audio_from_websocket(websocket)
|
| 74 |
+
client.add_frames(frame_data)
|
| 75 |
+
except WebSocketDisconnect:
|
| 76 |
+
return
|
| 77 |
|
| 78 |
if __name__ == '__main__':
|
| 79 |
freeze_support()
|
transcribe/whisper_llm_serve.py
CHANGED
|
@@ -36,9 +36,10 @@ class PyWhiperCppServe(ServeClientBase):
|
|
| 36 |
self.sample_rate = 16000
|
| 37 |
|
| 38 |
self.send_ready_state()
|
| 39 |
-
|
| 40 |
-
self.
|
| 41 |
-
self.run_in_thread(self.
|
|
|
|
| 42 |
|
| 43 |
self.text_sep = ""
|
| 44 |
|
|
@@ -46,6 +47,7 @@ class PyWhiperCppServe(ServeClientBase):
|
|
| 46 |
t = threading.Thread(target=func)
|
| 47 |
t.daemon = True
|
| 48 |
t.start()
|
|
|
|
| 49 |
|
| 50 |
def send_ready_state(self):
|
| 51 |
self.websocket.send(json.dumps({
|
|
@@ -72,7 +74,7 @@ class PyWhiperCppServe(ServeClientBase):
|
|
| 72 |
|
| 73 |
|
| 74 |
def get_frame_from_queue(self,):
|
| 75 |
-
while
|
| 76 |
try:
|
| 77 |
frame_np = self._frame_queue.get(timeout=0.1)
|
| 78 |
with self.lock:
|
|
@@ -145,7 +147,7 @@ class PyWhiperCppServe(ServeClientBase):
|
|
| 145 |
|
| 146 |
def speech_to_text(self):
|
| 147 |
# c = 0
|
| 148 |
-
while
|
| 149 |
if self.exit:
|
| 150 |
logger.info("Exiting speech to text thread")
|
| 151 |
break
|
|
@@ -221,11 +223,17 @@ class PyWhiperCppServe(ServeClientBase):
|
|
| 221 |
)
|
| 222 |
|
| 223 |
def send_to_client(self, data:TransResult):
|
| 224 |
-
|
| 225 |
-
|
| 226 |
-
|
| 227 |
-
|
| 228 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 229 |
|
| 230 |
|
| 231 |
def get_audio_chunk_for_processing(self):
|
|
@@ -240,5 +248,6 @@ class PyWhiperCppServe(ServeClientBase):
|
|
| 240 |
padded_audio = np.concatenate([silence, self.frames_np])
|
| 241 |
return padded_audio.copy()
|
| 242 |
|
| 243 |
-
def
|
| 244 |
-
|
|
|
|
|
|
| 36 |
self.sample_rate = 16000
|
| 37 |
|
| 38 |
self.send_ready_state()
|
| 39 |
+
self._translate_thread_stop = threading.Event()
|
| 40 |
+
self._frame_to_queue_thread_stop = threading.Event()
|
| 41 |
+
self.translate_thread = self.run_in_thread(self.speech_to_text)
|
| 42 |
+
self.frame_to_queue_thread = self.run_in_thread(self.get_frame_from_queue)
|
| 43 |
|
| 44 |
self.text_sep = ""
|
| 45 |
|
|
|
|
| 47 |
t = threading.Thread(target=func)
|
| 48 |
t.daemon = True
|
| 49 |
t.start()
|
| 50 |
+
return t
|
| 51 |
|
| 52 |
def send_ready_state(self):
|
| 53 |
self.websocket.send(json.dumps({
|
|
|
|
| 74 |
|
| 75 |
|
| 76 |
def get_frame_from_queue(self,):
|
| 77 |
+
while not self._frame_to_queue_thread_stop.is_set():
|
| 78 |
try:
|
| 79 |
frame_np = self._frame_queue.get(timeout=0.1)
|
| 80 |
with self.lock:
|
|
|
|
| 147 |
|
| 148 |
def speech_to_text(self):
|
| 149 |
# c = 0
|
| 150 |
+
while not self._translate_thread_stop.is_set():
|
| 151 |
if self.exit:
|
| 152 |
logger.info("Exiting speech to text thread")
|
| 153 |
break
|
|
|
|
| 223 |
)
|
| 224 |
|
| 225 |
def send_to_client(self, data:TransResult):
|
| 226 |
+
try:
|
| 227 |
+
coro = self.websocket.send_text(
|
| 228 |
+
Message(result=data, request_id=self.client_uid).model_dump_json(by_alias=True)
|
| 229 |
+
)
|
| 230 |
+
asyncio.run(coro)
|
| 231 |
+
except RuntimeError as e:
|
| 232 |
+
self.stop()
|
| 233 |
+
return
|
| 234 |
+
except Exception as e:
|
| 235 |
+
logger.error(e)
|
| 236 |
+
|
| 237 |
|
| 238 |
|
| 239 |
def get_audio_chunk_for_processing(self):
|
|
|
|
| 248 |
padded_audio = np.concatenate([silence, self.frames_np])
|
| 249 |
return padded_audio.copy()
|
| 250 |
|
| 251 |
+
def stop(self):
|
| 252 |
+
self._translate_thread_stop.set()
|
| 253 |
+
self._frame_to_queue_thread_stop.set()
|