Implemented new architecture

Created message service responsible for searching the prompts inside the recognized text and sending it to the client.

Created recognizer with two strategies: whisper and Dany's fast whisper.

Implemented file stack which works in the separated thread, sends the file to the recognizer and after that sends the message to the client (Rat, for example).

Dockerfile

@@ -1,20 +1,23 @@
 FROM python:3.10-slim
 
+ENV FLASK_APP=src/app.py
+ARG PIP_REQ_FILE=requirements.txt
+
 WORKDIR /app
 
-COPY requirements.txt /app
-RUN apt-get update && apt-get install git -y
-RUN pip3 install -r requirements.txt
-RUN pip3 install "git+https://github.com/openai/whisper.git" 
-RUN apt-get install -y ffmpeg
+RUN apt update && apt install git ffmpeg -y && \
+    pip3 install "git+https://github.com/openai/whisper.git"
 
-RUN whisper --model medium --language ru dummy.wav; exit 0
-RUN whisper --model small --language ru dummy.wav; exit 0
+RUN whisper --model medium --language ru dummy.wav; exit 0 && \
+    whisper --model small --language ru dummy.wav; exit 0
 
-COPY . .
+COPY src/ src/
+
+# Separate requirements installation to keep other dependencies
+# in cache
+COPY ${PIP_REQ_FILE} ${PIP_REQ_FILE}
+RUN pip3 install -r ${PIP_REQ_FILE}
 
 EXPOSE 5000
 
-ENV FLASK_APP=src/app.py
-
-CMD [ "python3", "-m" , "flask", "run", "--host=0.0.0.0"]
+CMD [ "python3", "-m" , "flask", "run", "--host=0.0.0.0"]

Makefile

@@ -0,0 +1,7 @@
+run:
+	PYTORCH_NO_CUDA_MEMORY_CACHING=1 \
+	PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True \
+	CUDA_LAUNCH_BLOCKING=1 \
+	FLASK_APP=src/app.py \
+	PYTORCH_CUDA_ALLOC_CONF=max_split_size_mb:128 \
+	flask run --host=0.0.0.0

requirements.txt

@@ -1,8 +1,62 @@
-flask==3.0.2
-Jinja2==3.1.3
+asgiref==3.7.2
+av==11.0.0
 blinker==1.7.0
-Werkzeug==3.0.1
+certifi==2024.2.2
+charset-normalizer==3.3.2
 click==8.1.7
+coloredlogs==15.0.1
+ctranslate2==4.0.0
+Cython==3.0.8
+dtw-python==1.3.1
+faster-whisper==1.0.0
+filelock==3.13.1
+Flask==3.0.2
+flatbuffers==23.5.26
+fsspec==2024.2.0
+huggingface-hub==0.21.3
+humanfriendly==10.0
+idna==3.6
 itsdangerous==2.1.2
+Jinja2==3.1.3
+llvmlite==0.42.0
 MarkupSafe==2.1.5
+more-itertools==10.2.0
+mpmath==1.3.0
+networkx==3.2.1
+numba==0.59.0
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==8.9.2.26
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.19.3
+nvidia-nvjitlink-cu12==12.3.101
+nvidia-nvtx-cu12==12.1.105
+onnxruntime==1.17.1
+openai-whisper @ git+https://github.com/openai/whisper.git@ba3f3cd54b0e5b8ce1ab3de13e32122d0d5f98ab
+packaging==23.2
+pillow==10.2.0
+protobuf==4.25.3
 python-dotenv==1.0.1
+PyYAML==6.0.1
+regex==2023.12.25
+requests==2.31.0
+scipy==1.12.0
+six==1.16.0
+sympy==1.12
+tiktoken==0.6.0
+tokenizers==0.15.2
+torch==2.2.1
+torchaudio==2.2.1
+torchvision==0.17.1
+tqdm==4.66.2
+triton==2.2.0
+typing_extensions==4.10.0
+urllib3==2.2.1
+Werkzeug==3.0.1
+whisper-timestamped==1.15.0

src/app.py

@@ -32,6 +32,7 @@ def recognize_files(handler_fn):
     results = []
 
     for filename, handle in request.files.items():
+        # 
         temp = NamedTemporaryFile()
         handle.save(temp)
         result = model.transcribe(temp.name, language=HARPYIA_LANGUAGE, initial_prompt=HARPYIA_PROMPT)

src/config.py

@@ -0,0 +1,12 @@
+import os
+import torch
+from dotenv import load_dotenv
+
+load_dotenv()
+
+HARPYIA_PROMPT = os.getenv('HARPYIA_PROMPT') or 'спасите помогите на помощь пожар'
+HARPYIA_MODEL = os.getenv('HARPYIA_MODEL') or 'medium'
+HARPYIA_LANGUAGE = os.getenv('HARPYIA_LANGUAGE') or 'ru'
+
+# Check if NVIDIA GPU is available
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"

src/file_stack.py

@@ -0,0 +1,32 @@
+from threading import Thread
+
+from recognizer import Recognizer
+from message import MessageComposer
+
+class WavStack:
+  def __init__(self, recognizer: Recognizer, message_composer: MessageComposer):
+    self._stack = []
+    self._recognizer = recognizer
+    self._message_composer = message_composer
+    self._running = False
+
+  def append(self, file):
+    self._stack.append(file)
+
+  def loop(self):
+    self._running = True
+    while self._running:
+      if self._stack:
+        file = self._stack.pop(0)
+        recognized_text = self._recognizer.recognize(file)
+        message = self._message_composer.compose(recognized_text)
+
+        if message.has_prompt():
+          message.send()
+
+  def start_loop_in_thread(self):
+    thread = Thread(target=self.loop)
+    thread.start()
+
+  def stop_loop(self):
+    self._running = False

src/message/__init__.py

@@ -0,0 +1,6 @@
+from message.prompt_service import PromptService
+from message.message_sender.message_sender import MessageSender
+from message.message_composer import MessageComposer
+from message.message import Message
+
+import message.message_sender as message_sender

src/message/message.py

@@ -0,0 +1,17 @@
+from message import PromptService, MessageSender
+
+class Message:
+  def __init__(self, prompt_service: PromptService, message_sender: MessageSender, \
+  recognized_text: str):
+    self._prompt_service = prompt_service
+    self._message_sender = message_sender
+    self._recognized_text = recognized_text
+
+  def has_prompt(self) -> bool:
+    return self._prompt_service.has_prompt(self._recognized_text)
+
+  def send(self):
+    self._message_sender.send(self._generate_response())
+
+  def _generate_response(self) -> str:
+    return self._prompt_service.filter_words_with_prompt(self._recognized_text)

src/message/message_composer.py

@@ -0,0 +1,9 @@
+from message import Message, PromptService, MessageSender
+
+class MessageComposer:
+  def __init__(self, prompt_service: PromptService, message_sender: MessageSender):
+    self._prompt_service = prompt_service
+    self._message_sender = message_sender
+
+  def compose(self, recognized_text) -> Message:
+    return Message(self._prompt_service, self._message_sender, recognized_text)

src/message/message_sender/__init__.py

@@ -0,0 +1,3 @@
+from message.message_sender.message_sender import MessageSender
+from message.message_sender.message_sender_strategy import MessageSenderStrategy
+from message.message_sender.rat_strategy import RatStrategy

src/message/message_sender/message_sender.py

@@ -0,0 +1,8 @@
+from message.message_sender import MessageSenderStrategy
+
+class MessageSender:
+  def __init__(self, strategy: MessageSenderStrategy):
+    self._strategy = strategy
+
+  def send(self, message):
+    self._strategy.send(message)

src/message/message_sender/message_sender_strategy.py

@@ -0,0 +1,6 @@
+from abc import ABC, abstractmethod
+
+class MessageSenderStrategy(ABC):
+  @abstractmethod
+  def send(self, message):
+    pass

src/message/message_sender/rat_strategy.py

@@ -0,0 +1,12 @@
+import requests
+
+from message.message_sender import MessageSenderStrategy
+
+MESSAGE_ENDPOINT = '/message'
+
+class RatStrategy(MessageSenderStrategy):
+  def __init__(self, url):
+    self._url = url
+
+  def send(self, message):
+    requests.post(self._url + MESSAGE_ENDPOINT, json={'message': message})

src/message/prompt_service.py

@@ -0,0 +1,16 @@
+class PromptService:
+  def __init__(self, prompt):
+    self._prompt = prompt
+
+  def has_prompt(self, text: str) -> bool:
+    for part in text.split(' '):
+      return part in self._prompt.split(' ')
+
+  def filter_words_with_prompt(self, text: str) -> str:
+    words = []
+
+    for part in text.split(' '):
+      if part in self._prompt.split(' '):
+        words.append(part)
+
+    return words

src/recognizer/__init__.py

@@ -0,0 +1,4 @@
+from recognizer.recognizer import Recognizer
+from recognizer.recognizer_strategy import RecognizerStrategy
+from recognizer.whisper_strategy import WhisperStrategy
+from recognizer.fast_whisper_strategy import FastWhisperStrategy

src/recognizer/fast_whisper_strategy.py

@@ -0,0 +1,5 @@
+from recognizer import RecognizerStrategy
+
+class FastWhisperStrategy(RecognizerStrategy):
+  def recognize(self, file) -> str:
+    return ''

src/recognizer/recognizer.py

@@ -0,0 +1,8 @@
+from recognizer import RecognizerStrategy
+
+class Recognizer:
+  def __init__(self, strategy: RecognizerStrategy):
+    self._strategy = strategy
+
+  def recognize(self, file) -> str:
+    self._strategy.recognize(file)

src/recognizer/recognizer_strategy.py

@@ -0,0 +1,6 @@
+from abc import ABC, abstractmethod
+
+class RecognizerStrategy(ABC):
+  @abstractmethod
+  def recognize(self, file) -> str:
+    pass

src/recognizer/whisper_strategy.py

@@ -0,0 +1,5 @@
+from recognizer import RecognizerStrategy
+
+class WhisperStrategy(RecognizerStrategy):
+  def recognize(self, file) -> str:
+    return ''