Add application file

Dockerfile

@@ -0,0 +1,31 @@
+FROM python:3.10
+
+RUN apt-get update && apt-get install -y \
+    git \
+    git-lfs \
+    ffmpeg \
+    libsm6 \
+    libxext6 \
+    cmake \
+    rsync \
+    libgl1 \
+    libglx-mesa0 \
+ && rm -rf /var/lib/apt/lists/* \
+ && git lfs install
+
+WORKDIR /app
+
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Hugging Face cache => /tmp
+ENV HF_HOME=/tmp/huggingface_cache
+ENV HF_HUB_CACHE=/tmp/huggingface_cache
+RUN mkdir -p /tmp/huggingface_cache && chmod -R 777 /tmp/huggingface_cache
+
+# Pre-download model into /tmp (optional for faster startup in Spaces docker build)
+RUN python -c "from faster_whisper import WhisperModel; WhisperModel('Systran/faster-whisper-small', device='cpu', compute_type='int8')"
+
+COPY . .
+
+CMD ["python", "app.py"]

app.py

@@ -0,0 +1,29 @@
+import os
+os.environ["HF_HOME"] = "/tmp/huggingface_cache"
+os.environ["HF_HUB_CACHE"] = "/tmp/huggingface_cache"
+
+from faster_whisper import WhisperModel
+import gradio as gr
+
+model = WhisperModel("Systran/faster-whisper-small", device="cpu", compute_type="int8")
+
+def transcribe_audio(audio_filepath, language):
+    if audio_filepath is None:
+        return "Error: No audio file provided."
+    lang = None if language == "auto" else language
+    segments, _ = model.transcribe(audio_filepath, beam_size=5, language=lang, vad_filter=True)
+    return " ".join(seg.text for seg in segments)
+
+iface = gr.Interface(
+    fn=transcribe_audio,
+    inputs=[
+        gr.Audio(type="filepath", label="Upload Audio File"),
+        gr.Radio(['en', 'bn', 'auto'], label="Select Language", value='auto')
+    ],
+    outputs="text",
+    title="⚡ Zen Speech-to-Text",
+    description="Upload audio → get transcription"
+)
+
+if __name__ == "__main__":
+    iface.launch(server_name="0.0.0.0", server_port=int(os.getenv("PORT", "7860")))

requirements.txt

@@ -0,0 +1,3 @@
+gradio>=4.0.0
+faster-whisper>=1.0.0
+ffmpeg-python