--- id: "/non-llm-neural-networks-ml-foundations/sequence-models/" title: "sequence models: 16 curated resources" url: "https://skillissue.dev/non-llm-neural-networks-ml-foundations/sequence-models/" --- # sequence models: 16 curated resources sequence models [Beginner](/non-llm-neural-networks-ml-foundations/beginner/index.md) [Intermediate](/non-llm-neural-networks-ml-foundations/intermediate/index.md) [Advanced](/non-llm-neural-networks-ml-foundations/advanced/index.md) [Expert](/non-llm-neural-networks-ml-foundations/expert/index.md) 16 resources · page 1 of 1 - ### [FunASR](/foundations/llm-fundamentals/funasr/index.md) by [ModelScope](https://www.modelscope.cn/) ModelScope FunASR GitHub repo: speech recognition toolkit for training, inference and streaming ASR. entity repo China zh - ### [AssemblyAI engineering blog](/foundations/llm-fundamentals/assemblyai-engineering-blog/index.md) by [AssemblyAI](https://assemblyai.com/) AssemblyAI blog with guides, model launches and voice-agent builds for speech AI. Intermediate learning_resource guide US en - ### [Karpathy: Unreasonable Effectiveness of RNNs](/foundations/llm-fundamentals/karpathy-unreasonable-effectiveness-of-rnns/index.md) by [Andrej](https://x.com/karpathy) Andrej Karpathy's 2015 essay The Unreasonable Effectiveness of Recurrent Neural Networks, with char-RNN examples. Intermediate learning_resource guide West en - ### [Recurrent Neural Networks and LSTM (Jürgen Schmidhuber)](/foundations/llm-fundamentals/lstm/index.md) by [Jürgen Schmidhuber](https://people.idsia.ch/) Jürgen Schmidhuber's IDSIA page on recurrent neural networks and LSTM, with history and references. Intermediate learning_resource guide EU-DE en - ### [Soniox Docs: Models](/foundations/llm-fundamentals/soniox-speech-model-registry-and-lifecycle-notes/index.md) by [Soniox](https://soniox.com/) Soniox models page listing speech-to-text model versions, changelog and deprecations. Intermediate learning_resource docs United States; Slovenia en - ### [Speechmatics technical articles](/foundations/llm-fundamentals/speechmatics-technical-articles/index.md) by [Speechmatics](https://speechmatics.com/) Speechmatics articles on speech recognition technology, product news and AI research. Intermediate learning_resource guide UK en - ### [Zoom Scribe API documentation](/foundations/llm-fundamentals/zoom-scribe-speech-to-text-api-documentation/index.md) by [Zoom](https://www.zoom.com/) Zoom Scribe API documentation: transcription service for many media formats, with modes and authentication details. Intermediate learning_resource docs United States en - ### [ESPnet](/foundations/llm-fundamentals/espnet/index.md) by [ESPnet](https://espnet.github.io/espnet/) ESPnet documentation: end-to-end speech processing toolkit with recipes for recognition, synthesis and translation. Advanced learning_resource docs Japan/global en - ### [GRU](/foundations/llm-fundamentals/gru/index.md) by [Kyunghyun Cho et al. (Université de Montréal)](https://www.umontreal.ca) arXiv paper (2014) introducing the RNN encoder–decoder with gated recurrent units (GRU) for machine translation. Advanced–Expert learning_resource paper EU-DE en - ### [GRU empirical evaluation](/foundations/llm-fundamentals/gru-empirical-evaluation/index.md) by [Junyoung Chung et al. (Université de Montréal)](https://www.umontreal.ca/) arXiv paper (2014) empirically comparing gated recurrent units (GRU) and LSTM on sequence modelling. Advanced–Expert learning_resource paper West en - ### [Montreal Forced Aligner](/foundations/llm-fundamentals/montreal-forced-aligner/index.md) by [Montreal Forced Aligner project (McGill University)](https://montreal-forced-aligner.readthedocs.io/) Montreal Forced Aligner documentation: tool for aligning speech audio with transcripts and training pronunciation models. Advanced learning_resource docs Canada/global en - ### [RWKV](/foundations/llm-fundamentals/rwkv/index.md) by [Bo Peng et al. (University of British Columbia)](https://www.ubc.ca/) arXiv paper (2023) introducing RWKV, a recurrent architecture trained in parallel like a transformer. Advanced–Expert learning_resource paper West en - ### [Efficiently Modeling Long Sequences with Structured State Spaces (S4)](/foundations/llm-fundamentals/s4-structured-state-spaces/index.md) by [Albert Gu et al. (Stanford University)](https://www.stanford.edu) arXiv paper (2021) "Efficiently Modeling Long Sequences with Structured State Spaces", introducing S4, structured state space models for long sequences. Advanced–Expert learning_resource paper West en - ### [WaveNet](/foundations/llm-fundamentals/wavenet/index.md) by [Aaron van den Oord et al. (DeepMind)](https://deepmind.google/) arXiv paper (2016) "WaveNet: A Generative Model for Raw Audio", introducing WaveNet, an autoregressive generative model of raw audio. Advanced–Expert learning_resource paper West en - ### [xLSTM (NXAI, Linz)](/foundations/llm-fundamentals/xlstm-nxai-linz/index.md) by [Maximilian Beck et al. (NXAI)](https://www.nx-ai.com/) arXiv paper (2024) introducing xLSTM, extended long short-term memory with exponential gating and matrix memory. Advanced–Expert learning_resource paper West en - ### [Mamba](/foundations/llm-fundamentals/mamba/index.md) by [Albert Gu and Tri Dao (Carnegie Mellon University)](https://www.cmu.edu/) arXiv paper (2023) introducing Mamba, linear-time sequence modelling with selective state spaces. Expert learning_resource paper West en [Plain-text Markdown copy](/non-llm-neural-networks-ml-foundations/sequence-models/index.md)