111 lines
3.5 KiB
Python
111 lines
3.5 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM-Omni project
|
|
"""
|
|
E2E Online tests for Qwen3-TTS model with text input and audio output.
|
|
|
|
These tests verify the /v1/audio/speech endpoint works correctly with
|
|
actual model inference, not mocks.
|
|
"""
|
|
|
|
import os
|
|
|
|
os.environ["VLLM_WORKER_MULTIPROC_METHOD"] = "spawn"
|
|
|
|
import pytest
|
|
|
|
from tests.helpers.mark import hardware_test
|
|
from tests.helpers.media import get_asset_path
|
|
from tests.helpers.runtime import OmniServerParams
|
|
from tests.helpers.stage_config import get_deploy_config_path
|
|
|
|
MODEL = "Qwen/Qwen3-TTS-12Hz-0.6B-Base"
|
|
DEFAULT_AUDIO_SPEECH_TIMEOUT_S = 180.0
|
|
|
|
# Vendored under tests/assets/qwen3_tts/clone_2.wav so the server does not need
|
|
# to fetch the reference audio over HTTPS at request time (CI runners in some
|
|
# regions cannot reach the original Aliyun OSS host; see issue #3263).
|
|
REF_AUDIO_URL = get_asset_path("qwen3_tts/clone_2.wav", as_data_url=True)
|
|
REF_TEXT = "Okay. Yeah. I resent you. I love you. I respect you. But you know what? You blew it! And thanks to you."
|
|
|
|
|
|
def get_prompt(prompt_type="text"):
|
|
"""Text prompt for text-to-audio tests (same as test_qwen3_omni - beijing test case)."""
|
|
prompts = {
|
|
"text": "The weather is nice today, perfect for a walk in the park.",
|
|
}
|
|
return prompts.get(prompt_type, prompts["text"])
|
|
|
|
|
|
def get_max_batch_size(size_type="few"):
|
|
"""Batch size for concurrent requests (same as test_qwen3_omni)."""
|
|
batch_sizes = {"few": 5, "medium": 100, "large": 256}
|
|
return batch_sizes.get(size_type, 5)
|
|
|
|
|
|
tts_server_params = [
|
|
pytest.param(
|
|
OmniServerParams(
|
|
model=MODEL,
|
|
stage_config_path=get_deploy_config_path("qwen3_tts.yaml"),
|
|
server_args=["--trust-remote-code"],
|
|
),
|
|
id="async_chunk",
|
|
)
|
|
]
|
|
|
|
|
|
@pytest.mark.advanced_model
|
|
@pytest.mark.tts
|
|
@hardware_test(res={"cuda": "L4"}, num_cards=1)
|
|
@pytest.mark.parametrize("omni_server", tts_server_params, indirect=True)
|
|
def test_text_to_audio_001(omni_server, online_client) -> None:
|
|
"""
|
|
Test text input processing and audio output via OpenAI API.
|
|
Deploy Setting: default yaml
|
|
Input Modal: text
|
|
Output Modal: audio
|
|
Input Setting: stream=False
|
|
Datasets: few requests
|
|
"""
|
|
|
|
request_config = {
|
|
"model": omni_server.model,
|
|
"input": get_prompt(),
|
|
"stream": False,
|
|
"timeout": DEFAULT_AUDIO_SPEECH_TIMEOUT_S,
|
|
"response_format": "wav",
|
|
"task_type": "Base",
|
|
"voice": "clone",
|
|
"ref_audio": REF_AUDIO_URL,
|
|
"ref_text": REF_TEXT,
|
|
}
|
|
online_client.send_audio_speech_request(request_config, request_num=get_max_batch_size("few"))
|
|
|
|
|
|
@pytest.mark.advanced_model
|
|
@pytest.mark.tts
|
|
@hardware_test(res={"cuda": "L4"}, num_cards=1)
|
|
@pytest.mark.parametrize("omni_server", tts_server_params, indirect=True)
|
|
def test_text_to_audio_002(omni_server, online_client) -> None:
|
|
"""
|
|
Test text input processing and audio output via OpenAI API.
|
|
Deploy Setting: default yaml
|
|
Input Modal: text
|
|
Output Modal: audio
|
|
Input Setting: stream=True
|
|
Datasets: single request
|
|
"""
|
|
request_config = {
|
|
"model": omni_server.model,
|
|
"input": get_prompt(),
|
|
"stream": True,
|
|
"stream_format": "audio",
|
|
"timeout": DEFAULT_AUDIO_SPEECH_TIMEOUT_S,
|
|
"response_format": "wav",
|
|
"task_type": "Base",
|
|
"voice": "clone",
|
|
"ref_audio": REF_AUDIO_URL,
|
|
"ref_text": REF_TEXT,
|
|
}
|
|
online_client.send_audio_speech_request(request_config)
|