TACOTRON2_WAVERNN_PHONE_LJSPEECH¶
- torchaudio.pipelines.TACOTRON2_WAVERNN_PHONE_LJSPEECH¶
Phoneme-based TTS pipeline with
Tacotron2trained on LJSpeech [Ito and Johnson, 2017] for 1,500 epochs, andWaveRNNvocoder trained on 8 bits depth waveform of LJSpeech [Ito and Johnson, 2017] for 10,000 epochs.The text processor encodes the input texts based on phoneme. It uses DeepPhonemizer to convert graphemes to phonemes. The model (en_us_cmudict_forward) was trained on CMUDict.
You can find the training script for Tacotron2 here. The following parameters were used;
win_length=1100,hop_length=275,n_fft=2048,mel_fmin=40, andmel_fmax=11025.You can find the training script for WaveRNN here.
Please refer to
torchaudio.pipelines.Tacotron2TTSBundle()for the usage.Example - “Hello world! T T S stands for Text to Speech!”
Example - “The examination and testimony of the experts enabled the Commission to conclude that five shots may have been fired,”
