CMsmartvoice / One-Shot-Voice-Cloning

:relaxed: One Shot Voice Cloning base on Unet-TTS
237 stars 40 forks source link

Is english text is supported? #12

Closed netrunner-exe closed 2 years ago

netrunner-exe commented 2 years ago
duration model load finished.
acoustics model load finished.
vocode model load finished.
['hello']
phoneme seq: sil hello sil

---------------------------------------------------------------------------

KeyError                                  Traceback (most recent call last)

[<ipython-input-40-71c2e65db483>](https://localhost:8080/#) in <module>
     29 text = "hello"
     30 
---> 31 syn_audio, _, _ = Tts_handel.one_shot_TTS(text, ref_audio)
     32 
     33 ipd.Audio(syn_audio, rate=16000)

2 frames

[/usr/local/lib/python3.7/dist-packages/tensorflow_tts/processor/multispk_voiceclone.py](https://localhost:8080/#) in text_to_sequence(self, text, inference)
    798         #print("text",text)
    799         for symbol in text.split():
--> 800             idx = self.symbol_to_id[symbol]
    801             sequence.append(idx)
    802 

KeyError: 'hello'
mingri-lt commented 2 years ago

only have chinese pre-model,and can not train english model.

no support english text

netrunner-exe commented 2 years ago

only have chinese pre-model,and can not train english model.

no support english text

It's a pity, a very promising model.