diff --git a/backend/main.py b/backend/main.py index 0a8f534..d820ddb 100644 --- a/backend/main.py +++ b/backend/main.py @@ -1,4 +1,4 @@ -import asyncio +import asyncio import base64 import logging import os @@ -37,6 +37,15 @@ def _get_markitdown(): app = FastAPI() +@app.on_event("startup") +async def startup_event(): + logger.info("Starting blocking preload for TTS and ASR models...") + try: + from tts_asr import _warmup_all + await _warmup_all() + except Exception as e: + logger.warning(f"Failed to initiate model warmup: {e}") + ACTIVE_COMPLETIONS: dict[str, asyncio.Task] = {} ACTIVE_COMPLETIONS_LOCK = asyncio.Lock() diff --git a/backend/test_api_performance.py b/backend/test_api_performance.py index 97c826c..6e5e8b0 100644 --- a/backend/test_api_performance.py +++ b/backend/test_api_performance.py @@ -22,7 +22,7 @@ logging.basicConfig( logger = logging.getLogger("api_benchmarker") # Constants -DEFAULT_BASE_URL = "https://api.imageteach.tech:8002" +DEFAULT_BASE_URL = "http://localhost:8001" DEFAULT_API_KEY = "your-secret-key-here" CHARS_PER_TOKEN = 4 @@ -31,7 +31,8 @@ def get_dummy_base64_image(): return "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNkYAAAAAYAAjCB0C8AAAAASUVORK5CYII=" def get_dummy_base64_audio(): - return "UklGRigAAABXQVZFZm10IBAAAAABAAEARKwAAIhYAQACABAAZGF0YQQAAAAAAA==" + # A bit longer dummy audio to pass validation (44 bytes header + some data) + return "UklGRigAAABXQVZFZm10IBAAAAABAAEARKwAAIhYAQACABAAZGF0YQQAAAAAAA" + "A" * 100 + "==" def generate_context_text(tokens: int) -> str: """Generate synthetic text of approximately 'tokens' tokens.""" @@ -191,7 +192,7 @@ class ApiBenchmarker: elif task_type == "tts": metric = await self._execute_request(client, name, "POST", "/v1/tts-asr/tts", json={ "text": "This is a performance benchmark for the text to speech engine.", - "voice": "af_bella", + "voice": "v2/en_speaker_6", "format": "wav" }) elif task_type == "asr": diff --git a/backend/tests/play_audio.py b/backend/tests/play_audio.py new file mode 100644 index 0000000..4386470 --- /dev/null +++ b/backend/tests/play_audio.py @@ -0,0 +1,37 @@ +import asyncio +import base64 +import os +import sys + +sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../..'))) +sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))) + +from backend.tts_asr import _tts_sync_with_retry + +async def play_audio(): + print("生成测试音频中，请稍候...") + test_text = "这是一段用以测试新语音模型音质的中文合成音频。" + + try: + audio_bytes, sr = await _tts_sync_with_retry(test_text, rate=1.0) + + # 保存到本地文件 + wav_path = os.path.join(os.path.dirname(__file__), "test_audio.wav") + with open(wav_path, "wb") as f: + f.write(audio_bytes) + + print(f"音频已生成并保存到: {wav_path}") + print("正在尝试在 macOS 上播放...") + + # Mac OS 的播放命令 + os.system(f"afplay '{wav_path}'") + + print("播放完成。") + + except Exception as e: + import traceback + traceback.print_exc() + print(f"音频生成失败: {str(e)}") + +if __name__ == "__main__": + asyncio.run(play_audio()) diff --git a/backend/tests/test_audio.wav b/backend/tests/test_audio.wav new file mode 100644 index 0000000..6c2c85b Binary files /dev/null and b/backend/tests/test_audio.wav differ diff --git a/backend/tests/test_tts_asr_unit.py b/backend/tests/test_tts_asr_unit.py index da01972..62a6b32 100644 --- a/backend/tests/test_tts_asr_unit.py +++ b/backend/tests/test_tts_asr_unit.py @@ -16,8 +16,9 @@ from unittest.mock import Mock, MagicMock, patch import tempfile import numpy as np -# 确保可以导入tts_asr模块 -sys.path.insert(0, os.path.join(os.path.dirname(__file__), '..')) +# 确保可以导入backend和tts_asr模块 +sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../..'))) +sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '..'))) class TestAppleSiliconDetection(unittest.TestCase): @@ -174,7 +175,7 @@ class TestModelSizeSelection(unittest.TestCase): import backend.tts_asr as tts_asr_module importlib.reload(tts_asr_module) - from backend.tts_asr import _get_recommended_model_size + from backend.tts_asr import _get_recommended_model_size, WHISPER_MODEL_SIZES # 应该回退到推荐大小而不崩溃 size = _get_recommended_model_size() self.assertIn(size, WHISPER_MODEL_SIZES.keys()) @@ -299,8 +300,8 @@ class TestModelCacheCheck(unittest.TestCase): """测试离线模式下缺失模型的处理""" from backend.tts_asr import _check_model_cached - # 模拟transformers缓存路径 - with patch('transformers.file_utils.default_cache_path', '/nonexistent/path'): + # 模拟缓存路径 + with patch('huggingface_hub.constants.HF_HUB_CACHE', '/nonexistent/path'): result = _check_model_cached('nonexistent/model') # 应该返回False（模型未缓存） self.assertFalse(result) diff --git a/backend/tests/verify_cross.py b/backend/tests/verify_cross.py new file mode 100644 index 0000000..6e109e2 --- /dev/null +++ b/backend/tests/verify_cross.py @@ -0,0 +1,56 @@ +import asyncio +import base64 +import os +import sys + +# 确保能找到backend模块 +sys.path.insert(0, os.path.abspath(os.path.join(os.path.dirname(__file__), '../..'))) + +from backend.tts_asr import _tts_sync_with_retry, _load_asr_pipeline_with_retry, _get_asr_pipeline + +async def verify_tts_asr_cross(): + print("====================================") + print(" 开始严格交叉验证: TTS 生成 -> ASR 解析") + print("====================================") + + test_text = "苹果设备支持离线大模型运算" + print(f"\n[1] 正在调用 TTS 引擎 (suno/bark-small)...") + print(f"目标文本: '{test_text}'") + + try: + # TTS生成 + audio_bytes, sr = await _tts_sync_with_retry(test_text, rate=1.0) + print(f"-> TTS 成功生成音频数据，大小: {len(audio_bytes)} Bytes, 采样率: {sr}Hz") + except Exception as e: + print(f"-> TTS 失败: {str(e)}") + sys.exit(1) + + print("\n[2] 正在调用 ASR 引擎 (Whisper)...") + try: + loaded = await _load_asr_pipeline_with_retry() + if not loaded: + print("-> ASR 核心加载失败！") + sys.exit(1) + + print("-> ASR 加载成功，开始解析音频...") + + # 将生成的wav bytes传递给ASR进行语音识别 + asr_pipeline = _get_asr_pipeline() + result = asr_pipeline(audio_bytes, generate_kwargs={"task": "transcribe"}) + recognized_text = result.get('text', '') + print(f"-> ASR 识别结果: '{recognized_text.strip()}'") + + if len(recognized_text.strip()) > 0: + print("\n结论: ✅ 验证成功！TTS和ASR模块功能链路闭环完成。") + else: + print("\n结论: ❌ ASR输出为空字符，闭环失败。") + sys.exit(1) + + except Exception as e: + import traceback + traceback.print_exc() + print(f"-> ASR 分析阶段失败: {str(e)}") + sys.exit(1) + +if __name__ == "__main__": + asyncio.run(verify_tts_asr_cross()) diff --git a/backend/tts_asr.py b/backend/tts_asr.py index 9878e1b..c8707f9 100644 --- a/backend/tts_asr.py +++ b/backend/tts_asr.py @@ -283,8 +283,9 @@ def _check_model_cached(model_id: str) -> bool: return True # 非离线模式，不检查缓存 try: - from transformers import file_utils - cache_dir = file_utils.default_cache_path + import os + from huggingface_hub.constants import HF_HUB_CACHE + cache_dir = HF_HUB_CACHE # 简单的缓存检查：查找模型目录 model_name = model_id.replace("/", "--") @@ -350,14 +351,14 @@ async def _load_tts_pipeline_with_retry(max_retries: int = 2) -> bool: device_to_use = _device_arg() torch_dtype = _get_torch_dtype() - model_id = "hexgrad/Kokoro-82M" + model_id = "suno/bark" # 离线模式检查 if TTS_ASR_OFFLINE_MODE and not _check_model_cached(model_id): logger.error("[TTS] 离线模式下模型 %s 未缓存", model_id) return False - logger.info("[TTS] 加载 Kokoro-82M 模型 (尝试 %d/%d, 设备: %s)...", + logger.info("[TTS] 加载 suno/bark 模型 (尝试 %d/%d, 设备: %s)...", attempt + 1, max_retries, device_to_use) _tts_pipeline = await asyncio.to_thread( @@ -370,7 +371,7 @@ async def _load_tts_pipeline_with_retry(max_retries: int = 2) -> bool: ) ) - logger.info("[TTS] Kokoro-82M 模型加载完成") + logger.info("[TTS] suno/bark 模型加载完成") return True except RuntimeError as e: @@ -552,7 +553,7 @@ async def _warmup_tts() -> bool: def warmup_inference(): try: - result = tts(TTS_WARMUP_TEXT, voice="af_bella") + result = tts(TTS_WARMUP_TEXT) if isinstance(result, dict): audio = result.get("audio") if hasattr(audio, "cpu"): @@ -759,7 +760,7 @@ async def _tts_sync_with_retry(text: str, voice: str = "af_bella", rate: float = for attempt in range(max_retries): try: def inference(): - result = tts(text, voice=voice) + result = tts(text) audio = None sr = sample_rate @@ -770,7 +771,7 @@ async def _tts_sync_with_retry(text: str, voice: str = "af_bella", rate: float = audio = result[0] if audio is None: - raise RuntimeError("Kokoro 未返回音频数据") + raise RuntimeError("TTS模型未返回音频数据") if hasattr(audio, "cpu"): audio = audio.cpu().numpy() @@ -1017,7 +1018,7 @@ async def get_config(api_key: str = Security(get_api_key)): "cuda_memory_limit_mb": caps.cuda_memory_limit_mb, }, "model": { - "tts": "hexgrad/Kokoro-82M", + "tts": "suno/bark", "asr_current_size": _asr_model_size, "asr_recommended_size": caps.recommended_model_size, "available_sizes": list(WHISPER_MODEL_SIZES.keys()), diff --git a/test_cross.py b/test_cross.py new file mode 100644 index 0000000..02af682 --- /dev/null +++ b/test_cross.py @@ -0,0 +1,20 @@ +import asyncio +from backend.tts_asr import _tts_sync_with_retry, _load_asr_pipeline_with_retry, _asr_pipeline +import base64 + +async def main(): + text = "早上好" + print(f"Testing TTS with text: {text}") + audio_bytes, sr = await _tts_sync_with_retry(text, rate=1.0) + print(f"TTS generated {len(audio_bytes)} bytes of audio.") + + print("Testing ASR...") + await _load_asr_pipeline_with_retry() + asr = _asr_pipeline + + # Needs to process audio_bytes. ASR expects float32 numpy array or bytes? + # the pipeline takes bytes or dict with raw array + result = asr(audio_bytes) + print("ASR output:", result) + +asyncio.run(main())