dasdas

Dockerfile

@@ -0,0 +1,28 @@
+# Use the official Python 3.9 image
+FROM python:3.10
+
+# Set the working directory to /code
+WORKDIR /code
+
+# Copy the current directory contents into the container at /code
+COPY ./requirements.txt /code/requirements.txt
+
+# Install requirements.txt 
+RUN pip install --no-cache-dir --upgrade -r /code/requirements.txt
+
+
+# Set up a new user named "user" with user ID 1000
+RUN useradd -m -u 1000 user
+# Switch to the "user" user
+USER user
+# Set home to the user's home directory
+ENV HOME=/home/user \
+	PATH=/home/user/.local/bin:$PATH
+
+# Set the working directory to the user's home directory
+WORKDIR $HOME/app
+
+# Copy the current directory contents into the container at $HOME/app setting the owner to the user
+COPY --chown=user . $HOME/app
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"]

main.py

@@ -0,0 +1,53 @@
+#uvicorn app:app --host 0.0.0.0 --port 8000 --reload
+
+# from fastapi import FastAPI
+# from transformers import pipeline
+
+# pipe = pipeline("automatic-speech-recognition", model="Pranjal12345/whisper-small-ne-pranjal")
+
+# audio_path = "/home/pranjal/Downloads/chinese_audio.mp3"
+
+# with open("/home/pranjal/Downloads/chinese_audio.mp3", "rb") as audio_file:
+#     audio_data = audio_file.read()
+
+# app = FastAPI()
+
+# @app.get("/")
+# def hello():
+#     output = pipe(input)
+#     return {"Output": output}
+
+
+
+
+
+
+from fastapi import FastAPI
+from transformers import WhisperProcessor, WhisperForConditionalGeneration
+import librosa
+
+app = FastAPI()
+
+# Load model and processor
+processor = WhisperProcessor.from_pretrained("openai/whisper-small")
+model = WhisperForConditionalGeneration.from_pretrained("openai/whisper-small")
+model.config.forced_decoder_ids = None
+
+# Path to your audio file
+audio_file_path = "/home/pranjal/Downloads/output.mp3"
+
+# Read the audio file
+audio_data, _ = librosa.load(audio_file_path, sr=16000)
+
+@app.get("/")
+def transcribe_audio():
+        # Process the audio data using the Whisper processor
+        input_features = processor(audio_data.tolist(), return_tensors="pt").input_features
+        
+        # Generate transcription
+        predicted_ids = model.generate(input_features)
+        transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)
+        
+        return {"transcription": transcription[0]}
+
+

requirements.txt

@@ -0,0 +1,7 @@
+librosa
+soundfile
+datasets
+fastapi
+uvicorn
+transformers
+Torch