
Speech-to-text, text-to-speech, speaker diarization, speech enhancement, source separation, and VAD using next-gen Kaldi with onnxruntime without Internet connection. Support embedded systems, Android, iOS, HarmonyOS, Raspberry Pi, RISC-V, RK NPU, Axera NPU, Ascend NPU, x86_64 servers, websocket server/client, support 12 programming languages.
Description in other languages
Statistics
Statistics as of Nov 17, 2026
GitHub stars
15,000
±0 (Oct 13〜)
Last commit
Nov 2026
Created on GitHub
Sep 1, 2022
Listed
—
Listed since the page was created
Stars over time
Show as a table
| Month | Stars |
|---|---|
| Dec 2025 | — |
| Jan 2026 | — |
| Feb 2026 | — |
| Mar 2026 | — |
| Apr 2026 | — |
| May 2026 | — |
| Jun 2026 | — |
| Jul 2026 | — |
| Aug 2026 | — |
| Sep 2026 | 15,000 |
| Oct 2026 | 15,000 |
| Nov 2026 | 15,000 |
Last snapshot of each month. Star counts of 1,000 or more are rounded to the nearest 100.
Use on PyPI
PyPI packages: sherpa-onnx, sherpa-onnx-core, sherpa-onnx-bin · Monthly figures to Oct 2026 (ClickPy)
Downloads, last 12 months
17,718,901
Share from Japan (last 12 months)
2.6%
PyPI packages that depend on it
57
24 as a required dependency
Monthly downloads on PyPI
Show as a table
| Month | downloads (month) |
|---|---|
| Jan 2019 | — |
| Feb 2019 | — |
| Mar 2019 | — |
| Apr 2019 | — |
| May 2019 | — |
| Jun 2019 | — |
| Jul 2019 | — |
| Aug 2019 | — |
| Sep 2019 | — |
| Oct 2019 | — |
| Nov 2019 | — |
| Dec 2019 | — |
| Jan 2020 | — |
| Feb 2020 | — |
| Mar 2020 | — |
| Apr 2020 | — |
| May 2020 | — |
| Jun 2020 | — |
| Jul 2020 | — |
| Aug 2020 | — |
| Sep 2020 | — |
| Oct 2020 | — |
| Nov 2020 | — |
| Dec 2020 | — |
| Jan 2021 | — |
| Feb 2021 | — |
| Mar 2021 | — |
| Apr 2021 | — |
| May 2021 | — |
| Jun 2021 | — |
| Jul 2021 | — |
| Aug 2021 | — |
| Sep 2021 | — |
| Oct 2021 | — |
| Nov 2021 | — |
| Dec 2021 | — |
| Jan 2022 | — |
| Feb 2022 | — |
| Mar 2022 | — |
| Apr 2022 | — |
| May 2022 | — |
| Jun 2022 | — |
| Jul 2022 | — |
| Aug 2022 | — |
| Sep 2022 | — |
| Oct 2022 | — |
| Nov 2022 | — |
| Dec 2022 | — |
| Jan 2023 | — |
| Feb 2023 | 2,474 |
| Mar 2023 | 5,462 |
| Apr 2023 | 7,806 |
| May 2023 | 7,074 |
| Jun 2023 | 10,102 |
| Jul 2023 | 22,781 |
| Aug 2023 | 52,315 |
| Sep 2023 | 37,759 |
| Oct 2023 | 37,577 |
| Nov 2023 | 42,127 |
| Dec 2023 | 42,615 |
| Jan 2024 | 35,248 |
| Feb 2024 | 24,809 |
| Mar 2024 | 34,420 |
| Apr 2024 | 45,820 |
| May 2024 | 43,408 |
| Jun 2024 | 70,650 |
| Jul 2024 | 235,132 |
| Aug 2024 | 51,351 |
| Sep 2024 | 63,668 |
| Oct 2024 | 63,633 |
| Nov 2024 | 61,664 |
| Dec 2024 | 65,466 |
| Jan 2025 | 66,248 |
| Feb 2025 | 63,312 |
| Mar 2025 | 74,163 |
| Apr 2025 | 80,109 |
| May 2025 | 86,616 |
| Jun 2025 | 88,867 |
| Jul 2025 | 98,202 |
| Aug 2025 | 144,285 |
| Sep 2025 | 213,540 |
| Oct 2025 | 207,250 |
| Nov 2025 | 229,848 |
| Dec 2025 | 227,215 |
| Jan 2026 | 264,150 |
| Feb 2026 | 277,300 |
| Mar 2026 | 392,754 |
| Apr 2026 | 435,706 |
| May 2026 | 563,858 |
| Jun 2026 | 1,289,402 |
| Jul 2026 | 1,180,504 |
| Aug 2026 | 3,193,429 |
| Sep 2026 | 2,909,090 |
| Oct 2026 | 6,755,645 |
Popular in the same category
NeMo SpeechNVIDIA-NeMo19kA scalable generative AI framework built for researchers and developers working on Large Language Models, Multimodal, and Speech AI (Automatic Speech Recognition and Text-to-Speech)
moonshinemoonshine-ai11kVery low latency speech to text, intent recognition, and text to speech, for building voice agents and interfaces.
FluidAudioFluidInference3kFrontier CoreML audio models in your apps — text-to-speech, speech-to-text, voice activity detection, and speaker diarization. In Swift, powered by SOTA open source.
CrispASRCrispStrobe732C++ ggml runtime hub for multilingual ASR and TTS models: Cohere Transcribe, Parakeet TDT, Voxtral, Canary 1B v2, etc, plus universal forced alignment, and more.
whisperopenai110kRobust Speech Recognition via Large-Scale Weak Supervision.
whisper.cppggml-org54kPort of OpenAI's Whisper model in C/C++.
Resources in similar research fields
- LFM2.5-Audio-1.5B-JP-GGUFLiquidAI506kQuantized GGUF versions of LiquidAI’s LFM 2.5‑Audio 1.5B JP model, including language, audio encoder, and vocoder weights (F32/F16/Q8_0/Q4_0), plus CLI/Server runners for ASR and TTS with llama.cpp.HF modelShared: Speech recognition・Speech synthesis
mlx-audioNeywa-Labs8kA text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.Shared: Speech recognition・Speech synthesis- kana-whispersbintuitions42kA fine‑tuned Whisper large‑v3‑turbo model that transcribes Japanese speech into katakana, serving as the ASR component of the Joyo Kanji Yomi Benchmark within the Sarashina2.2‑TTS project and powering the Kana CER Usage With Transformers pipeline.HF modelShared: Speech recognition・Speech synthesis
- japanese-hubert-base-phoneme-ctc-v2prj-beatrice7kFine‑tuned Japanese phoneme CTC model based on rinna/japanese-hubert-base, released as a higher‑accuracy v2 that excludes sentences containing “日本/方/明日”, removes those with “十/0/0” whose pyopenjtalk-plus pronunciation includes “ジュッ”, and changes the “言う” pronunciation from “イウ” to “ユー”.HF modelShared: Speech recognition・Speech synthesis
- japanese-hubert-base-phoneme-ctcprj-beatrice4kFine‑tuned Japanese phoneme CTC model based on rinna/japanese‑hubert‑base, trained with ReazonSpeech v2 data and pyopenjtalk‑plus labels, achieving improved accuracy in a new v2 release (prj-beatrice/japanese-hubert-base-phoneme-ctc-v2).HF modelShared: Speech recognition・Speech synthesis
- japanese-hubert-base-phoneme-ctc-v3prj-beatrice2kFine‑tuned Japanese HuBERT‑base for CTC phoneme recognition (v3), adding MeCab N‑best with pyopenjtalk‑plus post‑processing, a weighted loss combining CTC and MeCab costs, updated exclusion rules, and a new “ty” phoneme.HF modelShared: Speech recognition・Speech synthesis