Commit 1

Dockerfile

@@ -1,21 +1,19 @@
-FROM python:3.9-slim
-
-WORKDIR /app
-
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    curl \
-    software-properties-common \
-    git \
-    && rm -rf /var/lib/apt/lists/*
-
-COPY requirements.txt ./
-COPY src/ ./src/
-
-RUN pip3 install -r requirements.txt
-
-EXPOSE 8501
-
-HEALTHCHECK CMD curl --fail http://localhost:8501/_stcore/health
-
-ENTRYPOINT ["streamlit", "run", "src/streamlit_app.py", "--server.port=8501", "--server.address=0.0.0.0"]
+# Use official Python slim image
+FROM python:3.10-slim
+
+# Set working directory
+WORKDIR /app
+
+# Copy requirements and install
+COPY requirements.txt .
+RUN pip install --upgrade pip
+RUN pip install -r requirements.txt
+
+# Copy app files
+COPY . .
+
+# Expose port Streamlit uses
+EXPOSE 8501
+
+# Run Streamlit app
+CMD ["streamlit", "run", "app.py", "--server.port=8501", "--server.address=0.0.0.0"]

app.py

@@ -0,0 +1,100 @@
+import os
+import requests
+import tempfile
+import streamlit as st
+from moviepy.editor import VideoFileClip
+from speechbrain.inference.classifiers import EncoderClassifier
+
+st.set_page_config(page_title="Accent Classifier", page_icon="🗣️", layout="centered")
+
+# Custom CSS to change background color and style input box
+st.markdown(
+    """
+    <style>
+    .stApp {
+        background-color: #f0f0f0;
+    }
+    input[type="text"] {
+        background-color: white;
+        color: black;
+        border: 1px solid #ccc;
+        padding: 0.5rem;
+        border-radius: 5px;
+    }
+    .stTextInput > div > div > input {
+        background-color: white !important;
+        color: black !important;
+        border: 1px solid #ccc !important;
+    }
+    </style>
+    """,
+    unsafe_allow_html=True
+)
+
+MODEL_ID = "Jzuluaga/accent-id-commonaccent_ecapa"
+
+def download_video(url, output_path):
+    response = requests.get(url, stream=True)
+    if response.status_code == 200:
+        with open(output_path, "wb") as f:
+            for chunk in response.iter_content(1024):
+                f.write(chunk)
+        if not os.path.exists(output_path) or os.path.getsize(output_path) < 1024:
+            raise Exception("❌ Video download failed or file too small.")
+    else:
+        raise Exception("❌ Failed to download video.")
+
+def extract_audio(video_path, audio_path):
+    clip = VideoFileClip(video_path)
+    audio = clip.audio
+    audio.write_audiofile(audio_path, fps=16000, nbytes=2, codec='pcm_s16le', ffmpeg_params=["-ac", "1"])
+    clip.close()
+    audio.close()
+
+@st.cache_resource(show_spinner="Loading model...")
+def load_model():
+    classifier = EncoderClassifier.from_hparams(
+        source=MODEL_ID,
+        savedir=os.path.join(os.getcwd(), "accent-id-model")
+    )
+    return classifier
+
+def classify_accent(audio_path, classifier):
+    audio_path_clean = os.path.abspath(audio_path).replace('\\', '/')
+    if not os.path.exists(audio_path_clean):
+        raise FileNotFoundError(f"Audio file not found: {audio_path_clean}")
+    out_prob, score, index, label = classifier.classify_file(audio_path_clean)
+    return label, round(score.item() * 100, 2)
+
+# ---------------- UI ----------------
+st.title("🗣️ Accent Classifier from Video")
+st.markdown("Paste a direct **video URL (MP4)** and then press **Enter** or click **Identify the Accent**.")
+
+with st.form("url_form", clear_on_submit=False):
+    video_url = st.text_input("🔗 Video URL", placeholder="https://...")
+    submitted = st.form_submit_button("🗣️ Identify the Accent")
+
+if submitted:
+    if not video_url:
+        st.warning("⚠️ Please enter a video URL.")
+    else:
+        try:
+            if "dropbox.com" in video_url and "raw=1" not in video_url:
+                video_url = video_url.replace("dl=0", "raw=1").replace("?dl=0", "?raw=1")
+
+            with st.spinner("🔄 Downloading and processing video..."):
+                with tempfile.TemporaryDirectory() as tmpdir:
+                    video_path = os.path.join(tmpdir, "input_video.mp4")
+                    audio_path = os.path.join(tmpdir, "output_audio.wav")
+
+                    download_video(video_url, video_path)
+                    extract_audio(video_path, audio_path)
+                    classifier = load_model()
+                    label, confidence = classify_accent(audio_path, classifier)
+
+            st.success("✅ Accent classified successfully!")
+            st.markdown(f"### 🎯 Prediction: **{label}**")
+            st.markdown(f"🧠 Confidence: **{confidence}%**")
+            st.info(f"The speaker's accent is predicted to be **{label}** with **{confidence}%** confidence.")
+        except Exception as e:
+            st.error(f"❌ Error: {e}")

requirements.txt

@@ -1,3 +1,80 @@
-altair
-pandas
-streamlit
+altair==5.5.0
+attrs==25.3.0
+audioread==3.0.1
+blinker==1.9.0
+cachetools==5.5.2
+certifi==2025.4.26
+cffi==1.17.1
+charset-normalizer==3.4.2
+click==8.2.1
+colorama==0.4.6
+decorator==4.4.2
+filelock==3.18.0
+fsspec==2025.5.1
+gitdb==4.0.12
+GitPython==3.1.44
+huggingface-hub==0.32.2
+HyperPyYAML==1.2.2
+idna==3.10
+imageio==2.37.0
+imageio-ffmpeg==0.6.0
+Jinja2==3.1.6
+joblib==1.5.1
+jsonschema==4.24.0
+jsonschema-specifications==2025.4.1
+lazy_loader==0.4
+librosa==0.11.0
+llvmlite==0.44.0
+MarkupSafe==3.0.2
+moviepy==1.0.3
+mpmath==1.3.0
+msgpack==1.1.0
+narwhals==1.41.0
+networkx==3.4.2
+numba==0.61.2
+numpy==2.2.6
+packaging==24.2
+pandas==2.2.3
+pillow==11.2.1
+platformdirs==4.3.8
+pooch==1.8.2
+proglog==0.1.12
+protobuf==6.31.1
+pyarrow==20.0.0
+pycparser==2.22
+pydeck==0.9.1
+pydub==0.25.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.0
+pytz==2025.2
+PyYAML==6.0.2
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.3
+rpds-py==0.25.1
+ruamel.yaml==0.18.11
+ruamel.yaml.clib==0.2.12
+safetensors==0.5.3
+scikit-learn==1.6.1
+scipy==1.15.3
+sentencepiece==0.1.99
+six==1.17.0
+smmap==5.0.2
+soundfile==0.13.1
+soxr==0.5.0.post1
+speechbrain==1.0.3
+streamlit==1.45.1
+sympy==1.14.0
+tenacity==9.1.2
+threadpoolctl==3.6.0
+tokenizers==0.21.1
+toml==0.10.2
+torch==2.7.0
+torchaudio==2.7.0
+tornado==6.5.1
+tqdm==4.67.1
+transformers==4.52.3
+typing_extensions==4.13.2
+tzdata==2025.2
+urllib3==2.4.0
+watchdog==6.0.0