legco_ai_assistant/backend/app/services/asr_client.py

60 lines
1.7 KiB
Python

import struct
import base64
import logging
import zhconv
from openai import OpenAI
logger = logging.getLogger(__name__)
def float32_to_s16le(float32_bytes: bytes) -> bytes:
num_samples = len(float32_bytes) // 4
floats = struct.unpack(f"<{num_samples}f", float32_bytes)
int16_samples = [max(-32768, min(32767, int(f * 32767.0))) for f in floats]
return struct.pack(f"<{num_samples}h", *int16_samples)
def build_display_text(accumulated: str, current: str) -> str:
parts = [p for p in (accumulated, current) if p and p.strip()]
return " ".join(parts)
def _to_traditional(text: str) -> str:
if not text:
return text
return zhconv.convert(text, "zh-hant")
class ASRClient:
def __init__(self, settings):
self.settings = settings
def transcribe_full(self, audio_bytes: bytes, language: str = "yue") -> str:
audio_b64 = base64.b64encode(audio_bytes).decode()
data_url = f"data:audio/wav;base64,{audio_b64}"
client = OpenAI(
api_key=self.settings.dashscope_api_key,
base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
)
asr_options: dict = {}
if language != "auto":
asr_options["language"] = language
resp = client.chat.completions.create(
model=self.settings.asr_model_name,
messages=[{ # type: ignore[list-item]
"role": "user",
"content": [{
"type": "input_audio",
"input_audio": {"data": data_url},
}],
}],
extra_body={"asr_options": asr_options} if asr_options else None,
)
result = resp.choices[0].message.content or ""
return _to_traditional(result)