Small repo describing how to use Hugging Face's Wav2Vec2 with PyCTCDecode
Statistics for this project are still being loaded, please check back later.
DeepMind's Tacotron-2 Tensorflow implementation
Tensorflow implementation of contextualized word representations from bi-directional language models
An easy way to fine-tune Wav2Vec 2.0 for low-resource languages.
Applying "Load What You Need: Smaller Versions of Multilingual BERT" to LaBSE
Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.
Pipeline for training Language Models using PyTorch.
Audio super resolution using neural networks
Pytorch implementation of CS-Tacotron, a code-switching speech synthesis end-to-end generative TT...
Inference and training library for high-quality TTS models.
Speech-to-Text-WaveNet : End-to-end sentence level English speech recognition based on DeepMind's...
Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/tts)
Improving Language Model Performance through Smart Vocabularies
A TensorFlow implementation of Google's Tacotron speech synthesis with pre-trained model (unoffic...
OneShot Learning-based hotword detection.