Merge pull request #70 from Fosowl/dev

Fix : installation issues for linux system

Dockerfile

@@ -0,0 +1,26 @@
+# Use official Python 3.11 image as the base
+FROM python:3.11
+
+# Set working directory
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    gcc \
+    g++ \
+    gfortran \
+    libportaudio2 \
+    portaudio19-dev \
+    ffmpeg \
+    libavcodec-dev \
+    libavformat-dev \
+    libavutil-dev \
+    chromium \
+    chromium-driver \
+    && rm -rf /var/lib/apt/lists/*
+
+RUN pip cache purge
+
+COPY . .
+
+RUN BLIS_ARCH=generic pip install --no-cache-dir -r requirements.txt

requirements.txt

@@ -1,4 +1,6 @@
+setuptools>=75.6.0
 requests>=2.31.0
+numpy>=1.24.4
 colorama>=0.4.6
 python-dotenv>=1.0.0
 playsound>=1.3.0
@@ -7,17 +9,15 @@ transformers>=4.46.3
 torch>=2.4.1
 python-dotenv>=1.0.0
 ollama>=0.4.7
-scipy>=1.15.1
+scipy>=1.9.3
 kokoro>=0.7.12
-flask>=3.1.0
 soundfile>=0.13.1
 protobuf>=3.20.3
-termcolor>=2.5.0
-ipython>=8.34.0
-gliclass>=0.1.8
+termcolor>=2.4.0
+ipython>=8.13.0
 pyaudio>=0.2.14
 librosa>=0.10.2.post1
-selenium>=4.29.0
+selenium>=4.27.1
 markdownify>=1.1.0
 text2emotion>=0.0.5
 langid>=1.1.6

scripts/linux_install.sh

@@ -7,6 +7,17 @@ sudo apt-get update
 
 pip install --upgrade pip
 
+# install pyaudio
+pip install pyaudio
+# make sure essential tool are installed
+sudo apt install python3-dev python3-pip python3-wheel build-essential
+# install port audio
+sudo apt-get install portaudio19-dev python-pyaudio python3-pyaudio
+# install wheel
+pip install --upgrade pip setuptools wheel
+# install docker compose
+sudo apt install docker-compose
+
 # Install Python dependencies from requirements.txt
 pip3 install -r requirements.txt
 

server/Dockerfile

@@ -0,0 +1,14 @@
+FROM ubuntu:20.04
+
+WORKDIR /app
+
+RUN apt-get update && \
+    apt-get install -y python3 python3-pip && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+COPY requirements.txt .
+
+RUN pip3 install --no-cache-dir -r requirements.txt
+
+CMD ["python3", "--version"]

server/requirements.txt

@@ -0,0 +1,2 @@
+flask>=2.3.0
+ollama>=0.4.7

server/server.py

@@ -37,7 +37,10 @@ class GenerationState:
 
 state = GenerationState()
 
-def generate_response(history):  # Only takes history as an argument
+def generate_response_vllm(history):
+    pass
+
+def generate_response_ollama(history):  # Only takes history as an argument
     global state
     try:
         with state.lock:

setup.py

@@ -24,12 +24,11 @@ setup(
         "transformers>=4.46.3",
         "torch>=2.4.1",
         "ollama>=0.4.7",
-        "scipy>=1.15.1",
+        "scipy>=1.9.3",
         "kokoro>=0.7.12",
         "flask>=3.1.0",
         "protobuf>=3.20.3",
         "termcolor>=2.5.0",
-        "gliclass>=0.1.8",
         "ipython>=8.34.0",
         "librosa>=0.10.2.post1",
         "selenium>=4.29.0",

sources/speech_to_text.py

@@ -3,8 +3,8 @@ import queue
 import threading
 import numpy as np
 import torch
-from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
 import time
+from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
 import librosa
 import pyaudio
 
@@ -16,7 +16,6 @@ class AudioRecorder:
     AudioRecorder is a class that records audio from the microphone and adds it to the audio queue.
     """
     def __init__(self, format: int = pyaudio.paInt16, channels: int = 1, rate: int = 4096, chunk: int = 8192, record_seconds: int = 5, verbose: bool = False):
-        import pyaudio
         self.format = format
         self.channels = channels
         self.rate = rate