English TTS Model 108 Voices Fast_pitch Encoding Trained on Vctk Dataset at 22050Hz

English text-to-speech model containing 108 voices trained on the vctk dataset at 22050 Hz and is available to synthesize the en language.

Model Description

This English text-to-speech model contains 108 voices trained on the the VCTK dataset at 22050 Hz and is available to synthesize the en language. The model is based on the fast_pitch encoder.

pip install tts
tts --text "Hello, world!" --model_name tts_models/en/vctk/fast_pitch

Voice Samples

VCTK_p225 (M)

VCTK_p226 (M)

VCTK_p227 (M)

English

English is a West Germanic language that originated in England and is now one of the most widely spoken languages in the world. It belongs to the Indo-European language family and is closely related to German and Dutch. English has a diverse vocabulary and is known for its global influence as a lingua franca. It uses the Latin alphabet with modifications, including the addition of letters such as ð and þ in Old English. English features a complex phonetic system with a wide range of vowel and consonant sounds.

VCTK Dataset

The VCTK dataset is a multi-speaker English speech dataset that contains recordings from a diverse set of speakers. It is commonly used for training and evaluating speech synthesis and voice conversion models.

FastPitch

FastPitch is an advanced text-to-speech (TTS) model that combines the power of autoregressive generation and non-autoregressive duration modeling. It offers a fast and efficient way to synthesize speech from text. FastPitch achieves high-quality results while significantly reducing the inference time compared to traditional autoregressive models. This makes it suitable for real-time applications, interactive systems, and scenarios where low-latency speech synthesis is desired.