First commit

Dockerfile

@@ -0,0 +1,24 @@
+# Use an official Python image as the base image
+FROM python:3.8-slim
+
+# Set the working directory inside the container
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install
+
+# Install PyTorch
+RUN pip install --upgrade pip
+RUN pip install torch torchvision
+
+# Install Hugging Face Transformers and other dependencies
+RUN pip install transformers librosa deep-translator python-multipart fastapi uvicorn
+
+# Copy the main script
+COPY main.py .
+
+# Expose the port the app runs on
+EXPOSE 8000
+
+# Set the default command to run your FastAPI app or any other server
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "8000"]

main.py

@@ -0,0 +1,28 @@
+from fastapi import FastAPI, UploadFile, File
+from transformers import pipeline
+import librosa
+from deep_translator import GoogleTranslator
+import io
+
+app = FastAPI()
+
+print("Loading Speech Recognition")
+pipe = pipeline("automatic-speech-recognition", model="Akashpb13/xlsr_kurmanji_kurdish")
+print("Speech Recognition Loaded")
+
+print("Loading translator")
+translator = GoogleTranslator(source='ku', target='fr')
+print("Translator loaded")
+
+
+def speech2text(audio_data: bytes):
+    audio_array, _ = librosa.load(io.BytesIO(audio_data), sr=16000)    
+    output = pipe(audio_array)
+    return output["text"]
+
+@app.post("/transcribe")
+async def transcribe(file: UploadFile = File(...)):
+    audio_data = await file.read()
+    text_output = speech2text(audio_data)
+    translated = translator.translate(text_output)
+    return {"text": text_output, "translation": translated}