|
|
@@ -142,9 +142,9 @@ prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
|
|
|
for i, j in enumerate(cosyvoice.inference_zero_shot('收到好友从远方寄来的生日礼物，那份意外的惊喜与深深的祝福让我心中充满了甜蜜的快乐，笑容如花儿般绽放。', '希望你以后能够做的比我还好呦。', prompt_speech_16k, stream=False)):
|
|
|
torchaudio.save('zero_shot_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
|
|
|
|
|
|
-# fine grained control
|
|
|
+# fine grained control, for supported control, check cosyvoice/tokenizer/tokenizer.py#L248
|
|
|
prompt_speech_16k = load_wav('zero_shot_prompt.wav', 16000)
|
|
|
-for i, j in enumerate(cosyvoice.inference_cross_lingual('收到好友从远方寄来的生日礼物，那份意外的惊喜与深深的祝福让我心中充满了甜蜜的快乐，笑容如花儿般绽放。', prompt_speech_16k, stream=False)):
|
|
|
+for i, j in enumerate(cosyvoice.inference_cross_lingual('在他讲述那个荒诞故事的过程中，他突然[laughter]停下来，因为他自己也被逗笑了[laughter]。', prompt_speech_16k, stream=False)):
|
|
|
torchaudio.save('fine_grained_control_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
|
|
|
|
|
|
# instruct usage
|
Xiang Lyu