Renforcement de mots-clés

json_config = {
    "language": "en",
    "keywords": {
        "words": ["Mbappé", "Haaland", "Vinícius", "Bellingham", "Lewandowski"],
        "boost": 3,
    },
}

import unicodedata


def build_keywords(terms):
    strip = lambda s: "".join(
        c for c in unicodedata.normalize("NFKD", s) if not unicodedata.combining(c)
    )
    out = []
    for term in terms:
        for token in term.split():                       # split phrases into tokens
            for variant in (token, token.lower(), strip(token), strip(token).lower()):
                if variant not in out:
                    out.append(variant)
    return out


build_keywords(["Ferran Torres", "Mbappé"])
# ['Ferran', 'ferran', 'Torres', 'torres', 'Mbappé', 'mbappé', 'Mbappe', 'mbappe']

import asyncio
import gradium

TERMS = ["Kylian Mbappé", "Erling Haaland", "Vinícius Júnior", "Jude Bellingham"]


async def transcribe(audio_source):
    client = gradium.client.GradiumClient(api_key="your-api-key")

    async with client.stt_realtime(
        model_name="default",
        input_format="pcm",
        json_config={
            "language": "en",
            "delay_in_frames": 16,
            "keywords": {"words": build_keywords(TERMS), "boost": 3},
        },
    ) as stt:
        transcript = []

        async def producer():
            async for chunk in audio_source:
                await stt.send_audio(chunk)
            await stt.send_eos()

        async def consumer():
            async for msg in stt:
                if msg["type"] == "text":
                    transcript.append(msg["text"])
                elif msg["type"] == "end_of_stream":
                    return

        await asyncio.gather(producer(), consumer())
        return " ".join(transcript).strip()