Sequence Models
16 resources · page 1 of 1
FunASR
Creator not supplied; see original source.
ModelScope FunASR GitHub repo: speech recognition toolkit for training, inference and streaming ASR.
AssemblyAI engineering blog
Creator not supplied; see original source.
AssemblyAI blog with guides, model launches and voice-agent builds for speech AI.
Karpathy: Unreasonable Effectiveness of RNNs
Creator not supplied; see original source.
Andrej Karpathy's 2015 essay The Unreasonable Effectiveness of Recurrent Neural Networks, with char-RNN examples.
Recurrent Neural Networks and LSTM (Jürgen Schmidhuber)
Creator not supplied; see original source.
Jürgen Schmidhuber's IDSIA page on recurrent neural networks and LSTM, with history and references.
Soniox Docs: Models
Creator not supplied; see original source.
Soniox models page listing speech-to-text model versions, changelog and deprecations.
Speechmatics technical articles
Creator not supplied; see original source.
Speechmatics articles on speech recognition technology, product news and AI research.
Zoom Scribe API documentation
Creator not supplied; see original source.
Zoom Scribe API documentation: transcription service for many media formats, with modes and authentication details.
ESPnet
Creator not supplied; see original source.
ESPnet documentation: end-to-end speech processing toolkit with recipes for recognition, synthesis and translation.
GRU
Creator not supplied; see original source.
arXiv paper (2014) introducing the RNN encoder–decoder with gated recurrent units (GRU) for machine translation.
GRU empirical evaluation
Creator not supplied; see original source.
arXiv paper (2014) empirically comparing gated recurrent units (GRU) and LSTM on sequence modelling.
Montreal Forced Aligner
Creator not supplied; see original source.
Montreal Forced Aligner documentation: tool for aligning speech audio with transcripts and training pronunciation models.
RWKV
Creator not supplied; see original source.
arXiv paper (2023) introducing RWKV, a recurrent architecture trained in parallel like a transformer.
Efficiently Modeling Long Sequences with Structured State Spaces (S4)
Creator not supplied; see original source.
arXiv paper (2021) "Efficiently Modeling Long Sequences with Structured State Spaces", introducing S4, structured state space models for long sequences.
WaveNet
Creator not supplied; see original source.
arXiv paper (2016) "WaveNet: A Generative Model for Raw Audio", introducing WaveNet, an autoregressive generative model of raw audio.
xLSTM (NXAI, Linz)
Creator not supplied; see original source.
arXiv paper (2024) introducing xLSTM, extended long short-term memory with exponential gating and matrix memory.
Mamba
Creator not supplied; see original source.
arXiv paper (2023) introducing Mamba, linear-time sequence modelling with selective state spaces.