deep-learning cnn pytorch speech-recognition seq2seq neural-machine-translation nmt multimodality asr Updated Jan 5, 2023 Jupyter Notebook jayparks / tf-seq2seq Star 392 Code Issues Pull requests Sequence to sequence learning using TensorFlow. nlp machine-learning natural-language-processing deep...
In this paper we present FeatureBART, a linguistically motivated sequence-to-sequence monolingual pre-training strategy in which syntactic features such as lemma, part-of-speech and dependency labels are incorporated into the span prediction based pre-training framework (BART). These automatically extrac...
《Efficient Supervised Training of Audio Transformers for Music Representation Learning》(2023) GitHub: github.com/palonso/MAEST《VoiceFlow: Efficient Text-to-Speech with Rectified Flow Matching》(2023) GitHub: github.com/cantabile-kwok/VoiceFlow-TTS [fig1] ...