espnet2.sds.tts.chat_tts.ChatTTSModel

source

class espnet2.sds.tts.chat_tts.ChatTTSModel

Bases: AbsTTS

ChaTTS Model

Initializes the ChatTTSModel class.

Ensures that the ChatTTS library is properly installed and initializes the TTS engine.

forward(transcript: str) → Tuple[int, ndarray]

Converts a text transcript into an audio waveform using the ChatTTS system.

• Parameters:transcript (str) – The input text to be converted into speech.
• Returns: A tuple containing:
  • The sample rate of the audio (int).
  • The generated audio waveform as a NumPy array of type int16.
• Return type: Tuple[int, np.ndarray]

warmup()

Perform a single forward pass with dummy input to pre-load and warm up the model.