add files

Dockerfile

@@ -0,0 +1,59 @@
+FROM nvidia/cuda:11.7.1-cudnn8-devel-ubuntu22.04
+ENV DEBIAN_FRONTEND=noninteractive
+RUN apt-get update && \
+    apt-get upgrade -y && \
+    apt-get install -y --no-install-recommends \
+    git \
+    git-lfs \
+    wget \
+    curl \
+    # python build dependencies \
+    build-essential \
+    libssl-dev \
+    zlib1g-dev \
+    libbz2-dev \
+    libreadline-dev \
+    libsqlite3-dev \
+    libncursesw5-dev \
+    xz-utils \
+    tk-dev \
+    libxml2-dev \
+    libxmlsec1-dev \
+    libffi-dev \
+    liblzma-dev \
+    # gradio dependencies \
+    ffmpeg \
+    # fairseq2 dependencies \
+    libsndfile-dev && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+RUN useradd -m -u 1000 user
+USER user
+ENV HOME=/home/user \
+    PATH=/home/user/.local/bin:${PATH}
+WORKDIR ${HOME}/app
+
+RUN curl https://pyenv.run | bash
+ENV PATH=${HOME}/.pyenv/shims:${HOME}/.pyenv/bin:${PATH}
+ARG PYTHON_VERSION=3.10.12
+RUN pyenv install ${PYTHON_VERSION} && \
+    pyenv global ${PYTHON_VERSION} && \
+    pyenv rehash && \
+    pip install --no-cache-dir -U pip setuptools wheel
+
+COPY --chown=1000 ./requirements.txt /tmp/requirements.txt
+RUN pip install --no-cache-dir --upgrade -r /tmp/requirements.txt
+
+COPY --chown=1000 . ${HOME}/app
+ENV PYTHONPATH=${HOME}/app \
+    PYTHONUNBUFFERED=1 \
+    GRADIO_ALLOW_FLAGGING=never \
+    GRADIO_NUM_PORTS=1 \
+    GRADIO_SERVER_NAME=0.0.0.0 \
+    GRADIO_THEME=huggingface \
+    SYSTEM=spaces \
+    GRADIO_SERVER_PORT=7860
+EXPOSE 7860
+
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,28 @@
+import gradio as gr
+import os
+
+HF_API = os.getenv("HF_API")
+API_URL = os.getenv("API_URL")  # path to Seamlessm4t API endpoint
+
+DESCRIPTION = """
+# Seamlessm4t + Speaker Diarization + Voice Activity Detection
+Here we use seamlessm4t to generate captions for full audios. Audio can be of arbitrary length. """
+
+DUPLICATE = """
+To duplicate this repo, you have to give permission from three reopsitories and accept all user conditions: 
+1- https://huggingface.co/pyannote/voice-activity-detection
+2- hf.co/pyannote/segmentation
+3- hf.co/pyannote/speaker-diarization
+"""
+
+
+with gr.Blocks() as demo:
+    gr.Markdown(DESCRIPTION)
+    target_language = gr.Dropdown(choices=["French", "Spanish", "German"])
+    audio_source = gr.Radio(choices=["microphone", "file"])
+    mic_input = gr.Audio(source="microphone", visible=False)
+    file_input = gr.Audio(source="upload", visible=False)
+    output = gr.Textbox()
+    gr.Markdown(DUPLICATE)
+
+demo.queue(max_size=50).launch()

packages.txt

@@ -0,0 +1 @@
+ffmpeg

requirements.txt

@@ -0,0 +1,4 @@
+pyannote.audio
+pydub
+gradio_client
+gradio