Model I/O with files

import os
import base64
import requests

model_id = ""
# Read secrets from environment variables
baseten_api_key = os.environ["BASETEN_API_KEY"]

# Open a local file and base64-encode it (mono WAV, 48kHz sample rate)
with open("mymelody.wav", "rb") as f:
    encoded_str = base64.b64encode(f.read()).decode("utf-8")

# Build a JSON-serializable payload
data = {"prompts": ["happy rock", "energetic EDM", "sad jazz"], "melody": encoded_str, "duration": 8}

resp = requests.post(
    # Endpoint for production deployment, see API reference for more
    f"https://model-{model_id}.api.baseten.co/production/predict",
    headers={"Authorization": f"Bearer {baseten_api_key}"},
    json=data,
)

# Decode the base64 audio clips in the response and save them
for idx, clip in enumerate(resp.json()["data"]):
    with open(f"clip_{idx}.wav", "wb") as f:
        f.write(base64.b64decode(clip))

from tempfile import NamedTemporaryFile
import requests

# Get file content without blocking GPU
def preprocess(self, request):
    resp = requests.get(request["url"])
    return {"content": resp.content}

# Use file content in model inference
def predict(self, model_input):
    with NamedTemporaryFile() as fp:
        fp.write(model_input["content"])
        result = whisper.transcribe(
            self._model,
            fp.name,
            temperature=0,
            best_of=5,
            beam_size=5,
        )
        segments = [
            {"start": r["start"], "end": r["end"], "text": r["text"]}
            for r in result["segments"]
        ]
    return {
        "language": whisper.tokenizer.LANGUAGES[result["language"]],
        "segments": segments,
        "text": result["text"],
    }