Kamtera

/

persian-tts-female-glow_tts

like 10

i get this error when i use your model name.

ValueError: Unrecognized configuration class <class 'transformers.models.vits.configuration_vits.VitsConfig'> for this kind of AutoModel: AutoModelForTextToSpectrogram. Model type should be one of FastSpeech2ConformerConfig, SpeechT5Config.

other models are ok using this code snippet, but i get this error from yours. i'd be thankful if you can help solving it or do something about it. thanks

`text = ("سلام")
model_name = "Kamtera/persian-tts-male-vits"
tts = pipeline('text-to-speech', model=model_name, device=0)

result = tts(text)

Audio(result['audio'], rate=result['sampling_rate'])`