Alibaba Cloud Model Studio:SDK de Python de Qwen-ASR-Realtime - Referencia de API

Transmita audio a Qwen-ASR-Realtime mediante WebSocket y reciba resultados de transcripción en tiempo real a través del SDK de Python de DashScope.

Requisitos previos

Antes de comenzar, asegúrese de tener:

• SDK de DashScope 1.25.6 o posterior
• Una clave de API
• Comprensión del flujo de interacción

Ejemplo completo

ffmpeg -i your_audio.mp3 -ar 16000 -ac 1 -f s16le your_audio_file.pcm

import logging
import os
import base64
import signal
import sys
import time
import dashscope
from dashscope.audio.qwen_omni import *
from dashscope.audio.qwen_omni.omni_realtime import TranscriptionParams

def setup_logging():
    """Configure log output"""
    logger = logging.getLogger('dashscope')
    logger.setLevel(logging.DEBUG)
    handler = logging.StreamHandler(sys.stdout)
    handler.setLevel(logging.DEBUG)
    formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s')
    handler.setFormatter(formatter)
    logger.addHandler(handler)
    logger.propagate = False
    return logger

def init_api_key():
    """Initialize the API Key"""
    # The API Key differs between the Singapore and Beijing regions. Get your API Key: https://www.alibabacloud.com/help/model-studio/get-api-key
    # If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: dashscope.api_key = "sk-xxx"
    dashscope.api_key = os.environ.get('DASHSCOPE_API_KEY', 'YOUR_API_KEY')
    if dashscope.api_key == 'YOUR_API_KEY':
        print('[Warning] Using placeholder API key, set DASHSCOPE_API_KEY environment variable.')

class MyCallback(OmniRealtimeCallback):
    """Real-time recognition callback handler"""
    def __init__(self, conversation):
        self.conversation = conversation
        self.handlers = {
            'session.created': self._handle_session_created,
            'conversation.item.input_audio_transcription.completed': self._handle_final_text,
            'conversation.item.input_audio_transcription.text': self._handle_transcription_text,
            'input_audio_buffer.speech_started': lambda r: print('======Speech Start======'),
            'input_audio_buffer.speech_stopped': lambda r: print('======Speech Stop======')
        }

    def on_open(self):
        print('Connection opened')

    def on_close(self, code, msg):
        print(f'Connection closed, code: {code}, msg: {msg}')

    def on_event(self, response):
        try:
            handler = self.handlers.get(response['type'])
            if handler:
                handler(response)
        except Exception as e:
            print(f'[Error] {e}')

    def _handle_session_created(self, response):
        print(f"Start session: {response['session']['id']}")

    def _handle_final_text(self, response):
        print(f"Final recognized text: {response['transcript']}")

    def _handle_transcription_text(self, response):
        print(f"Got transcription result: {response['text'] + response['stash']}")

def read_audio_chunks(file_path, chunk_size=3200):
    """Read the audio file in chunks"""
    with open(file_path, 'rb') as f:
        while chunk := f.read(chunk_size):
            yield chunk

def send_audio(conversation, file_path, delay=0.1):
    """Send audio data"""
    if not os.path.exists(file_path):
        raise FileNotFoundError(f"Audio file {file_path} does not exist.")

    print("Processing audio file... Press 'Ctrl+C' to stop.")
    for chunk in read_audio_chunks(file_path):
        audio_b64 = base64.b64encode(chunk).decode('ascii')
        conversation.append_audio(audio_b64)
        time.sleep(delay)

def main():
    setup_logging()
    init_api_key()

    audio_file_path = "./your_audio_file.pcm"
    callback = MyCallback(conversation=None)
    conversation = OmniRealtimeConversation(
        model='qwen3-asr-flash-realtime',
        # The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. Configurations differ by region.
        url='wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime',
        callback=callback,
    )
    callback.conversation = conversation  # Inject conversation into the callback so its methods can be called within the callback

    def handle_exit(sig, frame):
        print('Ctrl+C pressed, exiting...')
        conversation.close()
        sys.exit(0)

    signal.signal(signal.SIGINT, handle_exit)

    conversation.connect()

    transcription_params = TranscriptionParams(
        language='zh',
        sample_rate=16000,
        input_audio_format="pcm"
    )

    conversation.update_session(
        output_modalities=[MultiModality.TEXT],
        enable_input_audio_transcription=True,
        transcription_params=transcription_params
    )

    try:
        send_audio(conversation, audio_file_path)
        # send session.finish and wait for finished and close
        conversation.end_session()
    except Exception as e:
        print(f"Error occurred: {e}")
    finally:
        conversation.close()
        print("Audio processing completed.")

if __name__ == '__main__':
    main()

Parámetros de solicitud

Constructor OmniRealtimeConversation

Cree una instancia de OmniRealtimeConversation con los siguientes parámetros.

from dashscope.audio.qwen_omni import OmniRealtimeConversation, OmniRealtimeCallback

class MyCallback(OmniRealtimeCallback):
    """Callback for real-time recognition"""
    def __init__(self, conversation):
        self.conversation = conversation
        self.handlers = {
            'session.created': self._handle_session_created,
            'conversation.item.input_audio_transcription.completed': self._handle_final_text,
            'conversation.item.input_audio_transcription.text': self._handle_stash_text,
            'input_audio_buffer.speech_started': lambda r: print('======Speech Start======'),
            'input_audio_buffer.speech_stopped': lambda r: print('======Speech Stop======')
        }

    def on_open(self):
        print('Connection opened')

    def on_close(self, code, msg):
        print(f'Connection closed, code: {code}, msg: {msg}')

    def on_event(self, response):
        try:
            handler = self.handlers.get(response['type'])
            if handler:
                handler(response)
        except Exception as e:
            print(f'[Error] {e}')

    def _handle_session_created(self, response):
        print(f"Start session: {response['session']['id']}")

    def _handle_final_text(self, response):
        print(f"Final recognized text: {response['transcript']}")

    def _handle_stash_text(self, response):
        print(f"Got stash result: {response['stash']}")

conversation = OmniRealtimeConversation(
        model='qwen3-asr-flash-realtime',
        # The following URL is for the Chinese mainland. For regions outside
        # the Chinese mainland, use
        # wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime instead.
        url='wss://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api-ws/v1/realtime',
        callback=MyCallback(conversation=None)  # Temporarily pass None and inject it later.
    )
# Inject self into the callback.
conversation.callback.conversation = conversation

Configuración de sesión

Después de conectarse, llame a update_session para configurar los parámetros de la sesión.

from dashscope.audio.qwen_omni import TranscriptionParams, MultiModality

transcription_params = TranscriptionParams(
    language='zh',
    sample_rate=16000,
    input_audio_format="pcm"
)

conversation.update_session(
    output_modalities=[MultiModality.TEXT],
    enable_turn_detection=True,
    turn_detection_type="server_vad",
    turn_detection_threshold=0.0,
    turn_detection_silence_duration_ms=400,
    enable_input_audio_transcription=True,
    transcription_params=transcription_params
)

TranscriptionParams

Configure los ajustes de reconocimiento de voz con el constructor TranscriptionParams.

transcription_params = TranscriptionParams(
    language='zh',
    sample_rate=16000,
    input_audio_format="pcm"
)

Interfaces clave

Clase OmniRealtimeConversation

from dashscope.audio.qwen_omni import OmniRealtimeConversation

Interfaz OmniRealtimeCallback

Subclasifique OmniRealtimeCallback e implemente sus métodos para manejar los eventos del servidor.

from dashscope.audio.qwen_omni import OmniRealtimeCallback