Add application file

Dockerfile

@@ -0,0 +1,18 @@
+# Use Python image
+FROM python:3.11-slim
+
+# Set workdir
+WORKDIR /app
+
+# Install dependencies
+COPY requirements.txt .
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+# Copy app files
+COPY . .
+
+# Expose the port Hugging Face expects
+EXPOSE 7860
+
+# Command to run FastAPI
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

codet5_model.py

@@ -0,0 +1,57 @@
+# from transformers import pipeline
+
+# #load Codet5 model
+# code_pipeline = pipeline("text-generation", model="Salesforce/codet5-base")
+
+# def generate_code(instruction: str) -> str:
+#   result = code_pipeline(instruction, max_length=256, clean_up_tokenization_spaces=True)
+#   return result[0]["generated_text"]
+
+
+# from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+# tokenizer = AutoTokenizer.from_pretrained("./models", trust_remote_code=True)
+# model = AutoModelForSeq2SeqLM.from_pretrained("./models", trust_remote_code=True)
+
+
+# def generate_code(instruction: str) -> str:
+#     prompt = f"Generate Python code for the following instruction: {instruction}"
+
+#     inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True)
+#     output = model.generate(**inputs, max_length=256)
+#     generated_code = tokenizer.decode(output[0], skip_special_tokens=True)
+
+#     return generated_code
+
+# from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+# tokenizer = AutoTokenizer.from_pretrained("./models")
+# model = AutoModelForSeq2SeqLM.from_pretrained("./models")
+
+# def generate_code(instruction: str) -> str:
+#     prompt = f"Generate Python code: {instruction}"
+#     inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True)
+#     output = model.generate(**inputs, max_length=256)
+#     return tokenizer.decode(output[0], skip_special_tokens=True)
+
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+# Global variables but not initialized
+tokenizer = None
+model = None
+
+def load_model():
+    global tokenizer, model
+    if tokenizer is None or model is None:
+        print("Loading CodeT5 model...")
+        tokenizer = AutoTokenizer.from_pretrained("Salesforce/codet5p-770m-py")
+        model = AutoModelForSeq2SeqLM.from_pretrained("Salesforce/codet5p-770m-py")
+        print("Model loaded.")
+
+def generate_code(instruction: str) -> str:
+    load_model()  # Ensure model is loaded before use
+    prompt = f"# Instruction: {instruction}\n# Python Code:\n"
+
+    inputs = tokenizer(prompt, return_tensors="pt", padding=True, truncation=True)
+    output = model.generate(**inputs, max_length=256)
+    return tokenizer.decode(output[0], skip_special_tokens=True)

ffmpeg_test.py

@@ -0,0 +1,8 @@
+from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
+
+model_id = "Salesforce/codet5p-770m-py"
+
+print("Downloading model...")
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForSeq2SeqLM.from_pretrained(model_id)
+print("Download complete.")

main.py

@@ -0,0 +1,41 @@
+import os
+import uvicorn
+from fastapi import FastAPI, UploadFile, File
+from whisper_model import transcribe_audio
+from codet5_model import generate_code
+from utils import save_audio_file
+from fastapi.middleware.cors import CORSMiddleware
+
+app = FastAPI()
+
+origins = [
+    "http://localhost:3000",
+    "http://127.0.0.1:3000",
+]
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=origins,
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+@app.post("/generate-code")
+async def voice_to_code(file: UploadFile = File(...)):
+    audio_path = save_audio_file(file)
+    instruction = transcribe_audio(audio_path)
+    code_output = generate_code(instruction)
+    return {
+        "instruction": instruction,
+        "code": code_output
+    }
+
+@app.get("/")
+def home():
+    return {"message": "Hello, World!"}
+
+
+if __name__ == "__main__":
+    port = int(os.environ.get("PORT", 8000))  # use PORT from env if available
+    uvicorn.run("main:app", host="0.0.0.0", port=port, reload=True)

utils.py

@@ -0,0 +1,12 @@
+import os
+from fastapi import UploadFile
+
+AUDIO_DIR = "audio_files"
+
+os.makedirs(AUDIO_DIR, exist_ok=True)
+
+def save_audio_file(file: UploadFile) -> str:
+  file_path = os.path.join(AUDIO_DIR, file.filename)
+  with open(file_path, "wb") as buffer:
+    buffer.write(file.file.read())
+  return file_path

whisper_model.py

@@ -0,0 +1,12 @@
+import os
+
+# Add FFmpeg directory to PATH
+os.environ["PATH"] += os.pathsep + r"C:\ffmpeg\bin"
+
+import whisper
+
+model = whisper.load_model("small")
+
+def transcribe_audio(file_path: str) -> str:
+  result = model.transcribe(file_path)
+  return result["text"]