Video Subtitling with Wav2Vec2

Video Subtitling with Wav2Vec2

tl;dr A step-by-step tutorial to automatically generate subtitles from a video using audio segmentation and Wav2Vec2. Practical Machine Learning - Learn Step-by-Step to Train a Model A great way to learn is by going step-by-step through the process of training and evaluating the model. Hit the Open in Colab button below to launch a Jupyter Notebook in the cloud with a step-by-step walkthrough. Continue on if you prefer reading the code here....

November 19, 2021 · 8 min · Eugene
Mandarin Text to Speech with Coqui TTS.

Mandarin Text to Speech with Coqui TTS

tl;dr A step-by-step tutorial to generate spoken mandarin audio from text (语音合成) using the Coqui TTS library. Practical Machine Learning - Learn Step-by-Step to Train a Model A great way to learn is by going step-by-step through the process of training and evaluating the model. Hit the Open in Colab button below to launch a Jupyter Notebook in the cloud with a step-by-step walkthrough. Continue on if you prefer reading the code here....

November 3, 2021 · 3 min · Eugene
Singlish Text to Speech with Malaya Speech

Singlish Text to Speech with Malaya Speech

tl;dr A step-by-step tutorial to generate spoken singlish audio from text automatically using a pipeline of a Malaya Speech model and applying speech enhancement. Practical Machine Learning - Learn Step-by-Step to Train a Model A great way to learn is by going step-by-step through the process of training and evaluating the model. Hit the Open in Colab button below to launch a Jupyter Notebook in the cloud with a step-by-step walkthrough....

October 21, 2021 · 4 min · Eugene
Text to Speech with Tacotron2 and WaveGlow. Image from Unsplash by Hrayr Movsisyan.

Text to Speech with Tacotron2 and WaveGlow

tl;dr A step-by-step tutorial to generate spoken audio from text automatically using a pipeline of Nvidia’s Tacotron2 and WaveGlow models and applying speech enhancement. Practical Machine Learning - Learn Step-by-Step to Train a Model A great way to learn is by going step-by-step through the process of training and evaluating the model. Hit the Open in Colab button below to launch a Jupyter Notebook in the cloud with a step-by-step walkthrough....

May 31, 2021 · 4 min · Eugene
Text to Speech with Silero. Image from Unsplash by Volodymyr Hryshchenko.

Text to Speech with Silero

tl;dr A step-by-step tutorial to generate spoken audio from text automatically using the enterprise-grade SileroTTS model and applying speech enhancement. Practical Machine Learning - Learn Step-by-Step to Train a Model A great way to learn is by going step-by-step through the process of training and evaluating the model. Hit the Open in Colab button below to launch a Jupyter Notebook in the cloud with a step-by-step walkthrough....

May 31, 2021 · 4 min · Eugene