One command to build TLG.fst for WeNet.
☆30Oct 11, 2022Updated 4 years ago
Alternatives and similar repositories for welm
Users that are interested in welm are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A ctc decoder for both online and offline asr model☆66Nov 18, 2023Updated 2 years ago
- faster inference☆27Jan 20, 2025Updated last year
- One command to start a streaming ASR server.☆12Oct 2, 2024Updated 2 years ago
- ☆13Mar 30, 2023Updated 3 years ago
- ☆23Oct 17, 2024Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- （WIP）long form speech generatoins☆30Apr 2, 2025Updated last year
- Torch Audio Forced Aligner for Mixed Chinese (Mandarin or Cantonese) and English.☆63Sep 5, 2025Updated last year
- CTC decoder with hotwords for ASR.☆42Sep 9, 2026Updated last month
- An N-gram punctuator for Chinese and English.☆20Oct 14, 2025Updated last year
- A streaming audio reader, processor, and writer built on top of soundfile, and PyAV (bindings for FFmpeg)☆39Oct 9, 2026Updated 3 weeks ago
- Grapheme-to-Phoneme for Mixed Chinese (Mandarin or Cantonese) and English.☆116Sep 2, 2026Updated 2 months ago
- ☆26Jun 19, 2025Updated last year
- Data manipulation and transformation for audio signal processing, powered by PyTorch☆10Sep 30, 2024Updated 2 years ago
- Open Source Speech/Text Data on AI☆19Sep 13, 2022Updated 4 years ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- magicspeech competition recipe☆18Jun 29, 2020Updated 6 years ago
- sherpa with mlx☆15Aug 2, 2025Updated last year
- ☆40Aug 15, 2021Updated 5 years ago
- WarpRNNT loss ported in Numba CPU/CUDA for Pytorch☆17Mar 11, 2022Updated 4 years ago
- For audio visualization and playback in Jupyter notebooks.☆19Aug 27, 2026Updated 2 months ago
- simple energy vad☆19Jun 3, 2017Updated 9 years ago
- Forced alignment decoder for Whisper.☆16Mar 13, 2024Updated 2 years ago
- Decoders from Kaldi using OpenFst☆36Oct 21, 2026Updated 2 weeks ago
- 流式识别近几年论文整理☆11Dec 2, 2020Updated 5 years ago
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- ☆10Feb 21, 2025Updated last year
- ☆13Mar 25, 2021Updated 5 years ago
- Production first, nn-based on-device signal processing toolkit.☆63May 30, 2023Updated 3 years ago
- ☆33Aug 6, 2021Updated 5 years ago
- ☆11Sep 8, 2025Updated last year
- ASR client for Triton ASR Service☆39Jan 12, 2026Updated 9 months ago
- FlashFunAsr: A lightweight vLLM implementation built from scratch for FunASR nano☆12Jan 5, 2026Updated 10 months ago
- Python wrapper for OpenFST and its extensions from Kaldi. Also support reading/writing ark/scp files☆56Updated this week
- Implementation of different noise embeddings for noise aware training of Kaldi acoustic models.☆13Feb 13, 2021Updated 5 years ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- ONNX Inference of Pyannote Segmentation☆100Dec 23, 2024Updated last year
- Dataset for Pinyin Regularization in Error Correction for Chinese Speech Recognition with Large Language Models in Interspeech 2024.☆16Jul 4, 2024Updated 2 years ago
- A Jupyter Widget for Web Audio Playing and Recording.☆11Aug 28, 2026Updated 2 months ago
- Code for paper "Dual-Path Style Learning for End-to-End Noise-Robust Speech Recognition"☆45May 23, 2023Updated 3 years ago
- ☆23Oct 30, 2024Updated 2 years ago
- NAACL 2025 main conference: "VoiceTextBlender: Augmenting Large Language Models with Speech Capabilities via Single-Stage Joint Speech-Te…☆13Apr 27, 2025Updated last year
- We Speech Transcript based on LLM, in 300 lines of code.☆182Jun 20, 2025Updated last year