src/playdiffusion/inputs.py

class InpaintInput:
    def __init__(self, input_text, output_text, input_word_times, audio, num_steps,
                 init_temp, init_diversity, guidance, rescale, topk,
                 audio_token_syllable_ratio):
        self.input_text = input_text
        self.output_text = output_text
        self.input_word_times = input_word_times
        self.audio = audio
        self.num_steps = num_steps
        self.init_temp = init_temp
        self.init_diversity = init_diversity
        self.guidance = guidance
        self.rescale = rescale
        self.topk = topk
        self.audio_token_syllable_ratio = audio_token_syllable_ratio


class TTSInput:
    def __init__(self, output_text, voice, num_steps, init_temp,
                 init_diversity, guidance, rescale, topk,
                 audio_token_syllable_ratio):
        self.output_text = output_text
        self.voice = voice
        self.num_steps = num_steps
        self.init_temp = init_temp
        self.init_diversity = init_diversity
        self.guidance = guidance
        self.rescale = rescale
        self.topk = topk
        self.audio_token_syllable_ratio = audio_token_syllable_ratio


class RVCInput:
    def __init__(self, source_speech, target_voice):
        self.source_speech = source_speech
        self.target_voice = target_voice