A Blog From Human-engineer-being: Recent Episodes
None
The post Finding the closest parent branch of a Git branch appeared first on A Blog From Human-engineer-being.
👉 Try out YourTTS demo 👉 Visit YourTTS project page 👉 Try YourTTS on Colab 👉 Try voice conversion with YourTTS on Colab YourTTS The recent surge of new end-to-end deep learning models has enabled new and exciting Text-to-Speech (TTS) use-cases with impressive natural-sounding results. However, most of these models are trained on massive datasets […]
The post YourTTS – Swiss Knife for Text-to-Speech appeared first on A Blog From Human-engineer-being.
This is one of the things I always need but I forget. So here is a piece of mind to check back. When you run your code with a breakpoint, you get an IPython shell for debugging. So you can use all the perks like autocomplete, magic functions, etc.
The post Using IPython (ipdb) for debugging appeared first on A Blog From Human-engineer-being.
The post Batch commit author renaming appeared first on A Blog From Human-engineer-being.
Original paper : https://arxiv.org/abs/2005.14165 It uses the same architecture as GPT-2. The largest model uses 170B parameters and trained with a batch size of 3.2 million. (Wow!). Training cost exceeds $12M. “Taking all these runs into account, the researchers estimated that building this model generated over 78,000 pounds of CO2 emissions in total—more than the […]
The post Notes on GPT-3 appeared first on A Blog From Human-engineer-being.
Model Samples: https://erogol.github.io/ddc-samples/ Colab Notebook (PyTorch): link Colab Notebook (Tensorflow): link Despite the success of the latest attention based end2end text2speech (TTS) models, they suffer from attention alignment problems at inference time. They occur especially with long-text inputs or out-of-domain character sequences. Here I like to propose a novel technique to fight against these alignment […]
The post Solving Attention Problems of TTS models with Double Decoder Consistency appeared first on A Blog From Human-engineer-being.
In this post, I like to introduce two methods that worked well in my experience for better attention alignment in Tacotron models. If you like to try your own you can visit Coqui TTS. The first method is Bidirectional Decoder and the second is Graves Attention (Gaussian Attention) with small tweaks. Bidirectional Decoder Bidirectional decoding […]
The post Two Attention Methods for Better Alignment with Tacotron appeared first on A Blog From Human-engineer-being.
Tacotron is a commonly used Text-to-Speech architecture. It is a very flexible alternative over traditional solutions. It only requires text and corresponding voice clips to train the model. It avoids the toil of fine-grained annotation of the data. However, Tacotron might also be very time demanding to train, especially if you don’t know the right […]
The post Gradual Training with Tacotron for Faster Convergence appeared first on A Blog From Human-engineer-being.
After a while of using tmux, you might see that you cannot reconnect it from another terminal windows with the error message error connecting to /tmp/tmux-1000/default (No such file or directory The solution is easy but hard to find. Here is the magical command worked for me. Hope it works for you too!
The post Recovering Lost Tmux Session appeared first on A Blog From Human-engineer-being.
Mixup – https://arxiv.org/abs/1710.09412.pdf Shake and Shake – https://arxiv.org/pdf/1705.07485.pdf Mix Feat – https://openreview.net/forum?id=HygT9oRqFX Speed perturbation (ASR) – https://www.danielpovey.com/files/2015_interspeech_augmentation.pdf Please feel free to extend the list…
The post Irregular Regularization Methods. appeared first on A Blog From Human-engineer-being.