update speak_reference_audio_path_or_name

Author: shibing624

README.md

@@ -199,7 +199,7 @@ 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='examples/voice_07.wav',  # 说话人音色参考
+   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
@@ -217,7 +217,7 @@ 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='examples/voice_07.wav',
+   speak_reference_audio_path_or_name='examples/voice_07.wav',
    text=text,
    output_path="gen.wav",
    emo_reference_audio_path="examples/emo_sad.wav",
@@ -237,7 +237,7 @@ 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='examples/voice_10.wav',
+   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
@@ -256,7 +256,7 @@ 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='examples/voice_12.wav',
+   speak_reference_audio_path_or_name='examples/voice_12.wav',
    text=text,
    output_path="gen.wav",
    emo_alpha=0.6,
@@ -277,7 +277,7 @@ 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='examples/voice_12.wav',
+   speak_reference_audio_path_or_name='examples/voice_12.wav',
    text=text,
    output_path="gen.wav",
    emo_alpha=0.6,

README_EN.md

@@ -199,7 +199,7 @@ from parrots.indextts import IndexTTS2
 tts = IndexTTS2()
 text = "The tavern is unconscionable, starting to auction rooms, ah, a bunch of fools."
 tts.infer(
-   speak_reference_audio_path='examples/voice_07.wav',  # Speaker timbre reference
+   speak_reference_audio_path_or_name='examples/voice_07.wav',  # Speaker timbre reference
    text=text,
    output_path="gen.wav",
    emo_reference_audio_path="examples/emo_sad.wav",  # Emotion reference audio
@@ -217,7 +217,7 @@ from parrots.indextts import IndexTTS2
 tts = IndexTTS2()
 text = "The tavern is unconscionable, starting to auction rooms, ah, a bunch of fools."
 tts.infer(
-   speak_reference_audio_path='examples/voice_07.wav',
+   speak_reference_audio_path_or_name='examples/voice_07.wav',
    text=text,
    output_path="gen.wav",
    emo_reference_audio_path="examples/emo_sad.wav",
@@ -237,7 +237,7 @@ from parrots.indextts import IndexTTS2
 tts = IndexTTS2()
 text = "Wow! This drop rate is so high! I'm blessed by luck!"
 tts.infer(
-   speak_reference_audio_path='examples/voice_10.wav',
+   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],  # Surprised emotion
@@ -256,7 +256,7 @@ from parrots.indextts import IndexTTS2
 tts = IndexTTS2()
 text = "Hide quickly! He's coming! He's coming to catch us!"
 tts.infer(
-   speak_reference_audio_path='examples/voice_12.wav',
+   speak_reference_audio_path_or_name='examples/voice_12.wav',
    text=text,
    output_path="gen.wav",
    emo_alpha=0.6,
@@ -277,7 +277,7 @@ tts = IndexTTS2()
 text = "Hide quickly! He's coming! He's coming to catch us!"
 emo_text = "You scared me to death! Are you a ghost?"  # Independent emotion description
 tts.infer(
-   speak_reference_audio_path='examples/voice_12.wav',
+   speak_reference_audio_path_or_name='examples/voice_12.wav',
    text=text,
    output_path="gen.wav",
    emo_alpha=0.6,

examples/demo_indextts.py

@@ -13,5 +13,5 @@
 
 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='wav/voice_12.wav', text=text, output_path="gen.wav", emo_alpha=0.6, use_emo_text=True,
+tts.infer(speak_reference_audio_path_or_name='wav/voice_12.wav', text=text, output_path="gen.wav", emo_alpha=0.6, use_emo_text=True,
           use_random=False, verbose=True)

examples/demo_indextts_with_emo.py

@@ -10,5 +10,5 @@
 
 tts = IndexTTS2()
 text = "他好帅啊，我好喜欢他！我们一起吃吃喝喝"
-tts.infer(speak_reference_audio_path='wav/voice_12.wav', text=text, output_path="happy.wav", emo_alpha=0.6, use_emo_text=True,
+tts.infer(speak_reference_audio_path_or_name='wav/voice_12.wav', text=text, output_path="happy.wav", emo_alpha=0.6, use_emo_text=True,
           use_random=False, verbose=True)