import os
import sys

sys.path.append('..')
from parrots import SpeechRecognition

pwd_path = os.path.abspath(os.path.dirname(__file__))

if __name__ == '__main__':
    m = SpeechRecognition()
    r = m.recognize_speech_from_file(os.path.join(pwd_path, 'tushuguan.wav'))
    print('[提示] 语音识别结果：', r)

from parrots import TextToSpeech

# 初始化 TTS 模型（无需手动配置路径）
m = TextToSpeech(
    speaker_model_path="shibing624/parrots-gpt-sovits-speaker-maimai",
    speaker_name="MaiMai",
    device="cpu",  # 或 "cuda" 使用 GPU
    half=False     # 设置为 True 使用半精度加速
)

# 生成语音
m.predict(
    text="你好，欢迎来到北京。这是一个合成录音文件的演示。Welcome to Beijing!",
    text_language="auto",  # 自动检测语言，也可指定 "zh", "en", "ja"
    output_path="output_audio.wav"
)

from parrots import TextToSpeech
import soundfile as sf
import numpy as np

m = TextToSpeech(
    speaker_model_path="shibing624/parrots-gpt-sovits-speaker-maimai",
    speaker_name="MaiMai",
)

# 流式生成语音
audio_chunks = []
for audio_chunk in m.predict_stream(
    text="这是一段较长的文本，将会被流式合成为语音。",
    text_language="zh",
    stream_chunk_size=20  # 控制延迟，越小延迟越低
):
    audio_chunks.append(audio_chunk)
    # 这里可以实时播放 audio_chunk

# 保存完整音频
full_audio = np.concatenate(audio_chunks)
sf.write("streaming_output.wav", full_audio, m.sampling_rate)

from parrots import TextToSpeech
from parrots.log import set_log_level, logger

# 设置日志级别
set_log_level("INFO")  # 可选: DEBUG, INFO, WARNING, ERROR

m = TextToSpeech(
    speaker_model_path="shibing624/parrots-gpt-sovits-speaker-maimai",
    speaker_name="MaiMai",
)

# 使用 logger
logger.info("开始语音合成...")
m.predict(
    text="你好，世界！",
    text_language="zh",
    output_path="output.wav"
)

from parrots.indextts import IndexTTS2

tts = IndexTTS2()
text = "你好，欢迎来到北京。这是一个合成录音文件的演示。"
tts.infer(text=text, output_path="gen.wav", verbose=True)

from parrots.indextts import IndexTTS2

tts = IndexTTS2()
text = "酒楼丧尽天良，开始借机竞拍房间，哎，一群蠢货。"
tts.infer(
   speak_reference_audio_path_or_name='examples/voice_07.wav',  # 说话人音色参考
   text=text,
   output_path="gen.wav",
   emo_reference_audio_path="examples/emo_sad.wav",  # 情感参考音频
   verbose=True
)

from parrots.indextts import IndexTTS2

tts = IndexTTS2()
text = "酒楼丧尽天良，开始借机竞拍房间，哎，一群蠢货。"
tts.infer(
   speak_reference_audio_path_or_name='examples/voice_07.wav',
   text=text,
   output_path="gen.wav",
   emo_reference_audio_path="examples/emo_sad.wav",
   emo_alpha=0.6,  # 情感强度 60%
   verbose=True
)

from parrots.indextts import IndexTTS2

tts = IndexTTS2()
text = "哇塞！这个爆率也太高了！欧皇附体了！"
tts.infer(
   speak_reference_audio_path_or_name='examples/voice_10.wav',
   text=text,
   output_path="gen.wav",
   emo_vector=[0, 0, 0, 0, 0, 0, 0.45, 0],  # 惊讶情感
   use_random=False,
   verbose=True
)

from parrots.indextts import IndexTTS2

tts = IndexTTS2()
text = "快躲起来！是他要来了！他要来抓我们了！"
tts.infer(
   speak_reference_audio_path_or_name='examples/voice_12.wav',
   text=text,
   output_path="gen.wav",
   emo_alpha=0.6,
   use_emo_text=True,  # 启用文本情感分析
   use_random=False,
   verbose=True
)

from parrots.indextts import IndexTTS2

tts = IndexTTS2()
text = "快躲起来！是他要来了！他要来抓我们了！"
emo_text = "你吓死我了！你是鬼吗？"  # 独立的情感描述
tts.infer(
   speak_reference_audio_path_or_name='examples/voice_12.wav',
   text=text,
   output_path="gen.wav",
   emo_alpha=0.6,
   use_emo_text=True,
   emo_text=emo_text,
   use_random=False,
   verbose=True
)

text = "之前你做DE5很好，所以这一次也DEI3做DE2很好才XING2，如果这次目标完成得不错的话，我们就直接打DI1去银行取钱。"