# k2-fsa/icefall

Repository: https://github.com/k2-fsa/icefall
Canonical: https://ross.abutalabs.com/products/icefall
Homepage: https://k2-fsa.github.io/icefall/
Language: Python
License: Apache-2.0
License Family: permissive
Last push: 2026-07-16T07:01:12+00:00

## Health v2 (maintenance only)
Score: 64/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 92, release rhythm 8, longevity 100
- inputs: {"age_days": 1894, "days_push": 48, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1482, forks 426 (observed 2026-08-28T04:04:51.153191+00:00)

## What it is
Icefall is a collection of speech recognition (ASR) and TTS training recipes built on the k2 and lhotse libraries, implemented in Python with PyTorch. It provides recipes for many public datasets and models such as Zipformer, Conformer, Transducer, CTC, and Whisper, with export paths to deployment frameworks like sherpa-onnx.

## Use cases
- train an automatic speech recognition model on librispeech
- fine-tune whisper on a custom speech dataset
- train a zipformer transducer ASR model
- build a TTS model with VITS on LJSpeech
- export a trained ASR model to onnx for deployment
- run forced alignment on speech transcripts
- reproduce ASR benchmarks like gigaspeech or wenetspeech

## When to choose
- you want to train state-of-the-art ASR models like Zipformer or Conformer transducers
- you need reproducible recipes for standard speech datasets
- you plan to deploy with the sherpa family of runtimes
- you want FST-based decoding, alignment, or language model rescoring with k2

## When to avoid
- you only need a ready-made inference engine rather than training recipes
- you want a simple pip-installable ASR API without GPU training setup
- you work outside speech/audio domains
- you need Windows-native training support without Docker

## Facets
- artifact type: library
- maturity: active
- function: speech-recognition, machine-learning, deep-learning, llm-training
- domain: speech-processing, machine-learning, deep-learning
- platform: python
- tags: asr, k2, lhotse, speech-recipes, tts, zipformer, transducer, model-training, pytorch, linux, gpu, docker

## Member repositories
- k2-fsa/icefall (main) score 64

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:51.153191+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:34:07.496250+00:00, confidence not recorded.
  - readme: https://github.com/k2-fsa/icefall (fetched 2026-08-28T04:04:51.153191+00:00, sha 637bf4b84f03)
  - homepage: https://k2-fsa.github.io/icefall/ (fetched 2026-08-29T11:40:41.618409+00:00, sha dc72b6a2adfb)
- Data as of 2026-08-30T08:39:29.467469+00:00.