tacotron and tacotron_asr
These are ecosystem siblings—one implements Tacotron for the TTS (text-to-speech) direction while the other adapts the same architecture for the reverse ASR (automatic speech recognition) direction, sharing the same foundational model design.
About tacotron
Kyubyong/tacotron
A TensorFlow Implementation of Tacotron: A Fully End-to-End Text-To-Speech Synthesis Model
This project helps you transform written text into natural-sounding spoken audio. You input text, and it produces an audio file of that text being read aloud, much like an audiobook. This is ideal for content creators, educators, or anyone needing to generate speech from text for various applications.
About tacotron_asr
Kyubyong/tacotron_asr
Speech Recognition Using Tacotron
This project offers a way to convert spoken audio into written text, essentially transcribing speech. You provide audio files containing spoken English, and it outputs the corresponding text. This is useful for anyone needing to automatically generate text from voice recordings, such as researchers working with spoken language data or content creators looking to subtitle audio.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work