asrfront

Super-fast frontend (feature extraction) for ASR models such as Whisper and SenseVoiceSmall.

native C core with no dependencies (own FFT, SIMD kernels with runtime CPU dispatch)
Python binding based on nanobind, zero-copy NumPy output
numerically matches the reference implementations (see Accuracy)

import asrfront

mel = asrfront.whisper.log_mel(audio)  # (80, 3000)
feat = asrfront.sensevoice.fbank(audio, cmvn="am.mvn")  # (T', 560)

Install

pip install asrfront

Wheels: Linux (x86_64, aarch64), Windows (x86_64); CPython 3.9+ (one abi3 wheel covers 3.12 and later). Building from source needs a C11/C++17 compiler.

Usage

audio is a 16 kHz mono waveform: a float array in [-1, 1], int16 PCM, a list, or a CPU torch tensor. Resampling and decoding are out of scope.

Whisper

from asrfront import whisper

mel = whisper.log_mel(audio)  # (80, 3000): pad/trim to 30 s like whisper
mel = whisper.log_mel(audio, n_mels=128)  # large-v3
mel = whisper.log_mel(audio, pad_or_trim=False)  # (80, len(audio) // 160)

batch = whisper.log_mel_batch([a1, a2, a3])  # (3, 80, 3000), multi-threaded

Equivalent to whisper.log_mel_spectrogram(whisper.pad_or_trim(audio), n_mels).

SenseVoice

from asrfront import sensevoice

feat = sensevoice.fbank(audio, cmvn="path/to/am.mvn")  # (ceil(T / 6), 560)
feats, lengths = sensevoice.fbank_batch([a1, a2], cmvn="path/to/am.mvn")  # zero-padded
raw = sensevoice.fbank_raw(audio)  # (T, 80) kaldi fbank only
shift, scale = sensevoice.load_cmvn("path/to/am.mvn")

Equivalent to FunASR's WavFrontend (torchaudio.compliance.kaldi.fbank on the int16-scaled waveform with a Hamming window, dither=0, then LFR m=7, n=6 and CMVN from am.mvn). dither= and seed= are available; the RNG is reseeded on every call so identical inputs give identical outputs.

Threads

All native calls release the GIL. The *_batch functions spread items over a thread pool (n_threads=None uses every available core); each Python thread uses its own native handle.

Performance

30 s of audio, single thread, Intel i5-14400F (AVX2), best of N runs (uv run --group ref --group bench python bench/compare.py):

	asrfront	reference	speed-up
Whisper log-mel (80 × 3000)	0.85–0.95 ms	openai-whisper `log_mel_spectrogram` (torch) 8.6–9.6 ms	~10x
		librosa STFT + mel (numpy) 6.6–7.0 ms	~7.7x
SenseVoice fbank + LFR + CMVN	1.3–1.4 ms	FunASR `WavFrontend` (torchaudio) 12–14 ms	~9–10x
kaldi fbank only	1.3 ms	`torchaudio.compliance.kaldi.fbank` 11–12 ms	~9x

Full results (thread scaling, input lengths, kernel variants, methodology): docs/benchmark.md.

Kernels process 8 frames at a time in SIMD lanes. On x86-64 an AVX2 build is selected at runtime when available (asrfront._ext.kernel_isa()); ASRFRONT_KERNELS=generic forces the baseline build. All variants give bit-identical results. Batch of 32 × 30 s: ~7.5 ms with 16 threads.

Accuracy

Maximum absolute error against float64 reference implementations (tests/python/reference.py) over 16 test signals (silence, tones, chirp, noise, clipping, DC offset, real speech, short and > 30 s inputs):

	worst case	speech	target
Whisper log-mel (80 and 128 mels)	4.0e-5	1.3e-5	1e-4
kaldi fbank (log domain)	7.7e-4	2.0e-4	1e-3
SenseVoice features with SenseVoiceSmall's `am.mvn`	1.1e-4

The whisper mel filters are bit-identical to whisper's mel_filters.npz. Against the original float32 libraries: ≤ 1e-4 vs. whisper (torch) and ≤ 2e-3 vs. torchaudio's kaldi fbank (torchaudio builds its mel banks in float32).

Development

uv sync                       # create .venv and build the extension (needs a C compiler)
uv run pytest                 # tests; add --group ref for torch/torchaudio comparisons
uv run --group ref pytest
uv run cmake -S . -B build/ctest -G Ninja -DASRFRONT_BUILD_TESTS=ON -DASRFRONT_BUILD_BENCH=ON
uv run cmake --build build/ctest && uv run ctest --test-dir build/ctest

The C API is in csrc/include/asrfront.h. The preprocessing of each model is documented step by step in docs/whisper.md and docs/sensevoice.md; see plan.md for design and implementation notes.

License

MIT. Test data in tests/data comes from openai/whisper (MIT); see tests/data/README.md.

Metadata

Release files for asrfront 0.1.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for asrfront 0.1.0
File	Size	Uploaded
asrfront-0.1.0.tar.gz	590.1 kB	Oct 10, 2026	Details

Built distributions (wheels)

Table of built distributions (wheels) for asrfront 0.1.0
File	Interpreter	ABI	Platform	Reset
asrfront-0.1.0-cp312-abi3-win_amd64.whl 116.0 kB Oct 10, 2026	CPython 3.12	abi3	Windows x86-64	Details
asrfront-0.1.0-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl 117.2 kB Oct 10, 2026	CPython 3.12	abi3	Linux glibc 2.27+ x86-64, Linux glibc 2.28+ x86-64	Details
asrfront-0.1.0-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl 104.0 kB Oct 10, 2026	CPython 3.12	abi3	Linux glibc 2.26+ ARM64, Linux glibc 2.28+ ARM64	Details
asrfront-0.1.0-cp311-cp311-win_amd64.whl 116.7 kB Oct 10, 2026	CPython 3.11	CPython 3.11	Windows x86-64	Details
asrfront-0.1.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl 121.7 kB Oct 10, 2026	CPython 3.11	CPython 3.11	Linux glibc 2.27+ x86-64, Linux glibc 2.28+ x86-64	Details
asrfront-0.1.0-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl 108.7 kB Oct 10, 2026	CPython 3.11	CPython 3.11	Linux glibc 2.26+ ARM64, Linux glibc 2.28+ ARM64	Details
asrfront-0.1.0-cp310-cp310-win_amd64.whl 116.3 kB Oct 10, 2026	CPython 3.10	CPython 3.10	Windows x86-64	Details
asrfront-0.1.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl 122.2 kB Oct 10, 2026	CPython 3.10	CPython 3.10	Linux glibc 2.27+ x86-64, Linux glibc 2.28+ x86-64	Details
asrfront-0.1.0-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl 109.0 kB Oct 10, 2026	CPython 3.10	CPython 3.10	Linux glibc 2.28+ ARM64, Linux glibc 2.26+ ARM64	Details
asrfront-0.1.0-cp39-cp39-win_amd64.whl 96.6 kB Oct 10, 2026	CPython 3.9	CPython 3.9	Windows x86-64	Details
asrfront-0.1.0-cp39-cp39-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl 116.2 kB Oct 10, 2026	CPython 3.9	CPython 3.9	Linux glibc 2.27+ x86-64, Linux glibc 2.28+ x86-64	Details
asrfront-0.1.0-cp39-cp39-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl 103.2 kB Oct 10, 2026	CPython 3.9	CPython 3.9	Linux glibc 2.26+ ARM64, Linux glibc 2.28+ ARM64	Details

Total release size: 1.9 MB

Release files / asrfront-0.1.0.tar.gz

Download URL	asrfront-0.1.0.tar.gz
Size	590.1 kB
Tags	Source
SHA-256 checksum How to use checksums	`d31883cbc2ea6903c42deabdb1d0116b5ee99ec6639e6fec7cd94a81898f937b`
BLAKE2b-256 checksum How to use checksums	`e26fceaafea026b348abb5ea0445d9dd12c53a15323e1d010934455e444ce00b`
Upload date	Oct 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/sjjeong94/asrfront
Publishing commit: github.com/sjjeong94/asrfront/tree/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59

Workflow

Publishing configuration: github.com/sjjeong94/asrfront/blob/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59/.github/workflows/wheels.yml
Publishing logs: github.com/sjjeong94/asrfront/actions/runs/38024623597/attempts/1

Artifact

Subject: asrfront-0.1.0.tar.gz
SHA-256 checksum: d31883cbc2ea6903c42deabdb1d0116b5ee99ec6639e6fec7cd94a81898f937b Verifying attestations

Release files / asrfront-0.1.0-cp312-abi3-win_amd64.whl

Download URL	asrfront-0.1.0-cp312-abi3-win_amd64.whl
Size	116.0 kB
Tags	CPython 3.12 Windows x86-64 abi3
SHA-256 checksum How to use checksums	`e9d0ee7d091e457700265895b562a41dcfb6f9bd80f467c2a08e4338f5956c31`
BLAKE2b-256 checksum How to use checksums	`2c8ae62a0a639ea0c2743927b6b77079866846bab271dd966d01edf303346be2`
Upload date	Oct 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/sjjeong94/asrfront
Publishing commit: github.com/sjjeong94/asrfront/tree/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59

Workflow

Publishing configuration: github.com/sjjeong94/asrfront/blob/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59/.github/workflows/wheels.yml
Publishing logs: github.com/sjjeong94/asrfront/actions/runs/38024623597/attempts/1

Artifact

Subject: asrfront-0.1.0-cp312-abi3-win_amd64.whl
SHA-256 checksum: e9d0ee7d091e457700265895b562a41dcfb6f9bd80f467c2a08e4338f5956c31 Verifying attestations

Release files / asrfront-0.1.0-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Download URL	asrfront-0.1.0-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Size	117.2 kB
Tags	CPython 3.12 Linux glibc 2.27+ x86-64 Linux glibc 2.28+ x86-64 abi3
SHA-256 checksum How to use checksums	`2ddf00f917cc6d1ecc265474d46a0a5221c2242e9e13ba54b1b964c3517b8ee8`
BLAKE2b-256 checksum How to use checksums	`923e60b59867e8b9306b6d3034b9920a72d90fc9204f75991750258ce3e4e491`
Upload date	Oct 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/sjjeong94/asrfront
Publishing commit: github.com/sjjeong94/asrfront/tree/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59

Workflow

Publishing configuration: github.com/sjjeong94/asrfront/blob/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59/.github/workflows/wheels.yml
Publishing logs: github.com/sjjeong94/asrfront/actions/runs/38024623597/attempts/1

Artifact

Subject: asrfront-0.1.0-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
SHA-256 checksum: 2ddf00f917cc6d1ecc265474d46a0a5221c2242e9e13ba54b1b964c3517b8ee8 Verifying attestations

Release files / asrfront-0.1.0-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl

Download URL	asrfront-0.1.0-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
Size	104.0 kB
Tags	CPython 3.12 Linux glibc 2.26+ ARM64 Linux glibc 2.28+ ARM64 abi3
SHA-256 checksum How to use checksums	`50a9f9939e06ce30252c00d6a9e40c0be314ff84363528980da92f9f3ad0f207`
BLAKE2b-256 checksum How to use checksums	`ac8753a3115af23a948e9dcefc3dfda36d9035390d560ad4d9002dc259899d75`
Upload date	Oct 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/sjjeong94/asrfront
Publishing commit: github.com/sjjeong94/asrfront/tree/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59

Workflow

Publishing configuration: github.com/sjjeong94/asrfront/blob/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59/.github/workflows/wheels.yml
Publishing logs: github.com/sjjeong94/asrfront/actions/runs/38024623597/attempts/1

Artifact

Subject: asrfront-0.1.0-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
SHA-256 checksum: 50a9f9939e06ce30252c00d6a9e40c0be314ff84363528980da92f9f3ad0f207 Verifying attestations

Release files / asrfront-0.1.0-cp311-cp311-win_amd64.whl

Download URL	asrfront-0.1.0-cp311-cp311-win_amd64.whl
Size	116.7 kB
Tags	CPython 3.11 Windows x86-64
SHA-256 checksum How to use checksums	`f40c362a10fd40b3cb823b1e815f66d521e431661b3854a65f0f21157ebba2a8`
BLAKE2b-256 checksum How to use checksums	`ab402206a005db1ca90cacaf5e45f0a51f219a4ab7cd4993261d2edbf3c671aa`
Upload date	Oct 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/sjjeong94/asrfront
Publishing commit: github.com/sjjeong94/asrfront/tree/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59

Workflow

Publishing configuration: github.com/sjjeong94/asrfront/blob/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59/.github/workflows/wheels.yml
Publishing logs: github.com/sjjeong94/asrfront/actions/runs/38024623597/attempts/1

Artifact

Subject: asrfront-0.1.0-cp311-cp311-win_amd64.whl
SHA-256 checksum: f40c362a10fd40b3cb823b1e815f66d521e431661b3854a65f0f21157ebba2a8 Verifying attestations

Release files / asrfront-0.1.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Download URL	asrfront-0.1.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Size	121.7 kB
Tags	CPython 3.11 Linux glibc 2.27+ x86-64 Linux glibc 2.28+ x86-64
SHA-256 checksum How to use checksums	`50c93fe3856d9d869c0a6792ffd1050601c2c012b4fe5dbbbf43f25aa3f096cd`
BLAKE2b-256 checksum How to use checksums	`cdd15312c521d5efdf95e9e618e184806b34989b0f2beac9bf8a5fcc8c2d9861`
Upload date	Oct 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/sjjeong94/asrfront
Publishing commit: github.com/sjjeong94/asrfront/tree/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59

Workflow

Publishing configuration: github.com/sjjeong94/asrfront/blob/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59/.github/workflows/wheels.yml
Publishing logs: github.com/sjjeong94/asrfront/actions/runs/38024623597/attempts/1

Artifact

Subject: asrfront-0.1.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
SHA-256 checksum: 50c93fe3856d9d869c0a6792ffd1050601c2c012b4fe5dbbbf43f25aa3f096cd Verifying attestations

Release files / asrfront-0.1.0-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl

Download URL	asrfront-0.1.0-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
Size	108.7 kB
Tags	CPython 3.11 Linux glibc 2.26+ ARM64 Linux glibc 2.28+ ARM64
SHA-256 checksum How to use checksums	`2e9be69ad085d1d4e230dce2fadda8bb30ca390b1abb6f74522f14235192e380`
BLAKE2b-256 checksum How to use checksums	`30d07e0b909f150bc474d4c8880537eda1b19556f7e9aacc0fb84cfb1f33c99d`
Upload date	Oct 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/sjjeong94/asrfront
Publishing commit: github.com/sjjeong94/asrfront/tree/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59

Workflow

Publishing configuration: github.com/sjjeong94/asrfront/blob/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59/.github/workflows/wheels.yml
Publishing logs: github.com/sjjeong94/asrfront/actions/runs/38024623597/attempts/1

Artifact

Subject: asrfront-0.1.0-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
SHA-256 checksum: 2e9be69ad085d1d4e230dce2fadda8bb30ca390b1abb6f74522f14235192e380 Verifying attestations

Release files / asrfront-0.1.0-cp310-cp310-win_amd64.whl

Download URL	asrfront-0.1.0-cp310-cp310-win_amd64.whl
Size	116.3 kB
Tags	CPython 3.10 Windows x86-64
SHA-256 checksum How to use checksums	`5744b34fb020ee8710286ce61a20806f6fc5e73a7b9101f0f65fe88a3b2540f3`
BLAKE2b-256 checksum How to use checksums	`fd26d517d2ef9fe1bb59a247f4d891a18ab6ea87aaf6ff61eb329509792950a9`
Upload date	Oct 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/sjjeong94/asrfront
Publishing commit: github.com/sjjeong94/asrfront/tree/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59

Workflow

Publishing configuration: github.com/sjjeong94/asrfront/blob/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59/.github/workflows/wheels.yml
Publishing logs: github.com/sjjeong94/asrfront/actions/runs/38024623597/attempts/1

Artifact

Subject: asrfront-0.1.0-cp310-cp310-win_amd64.whl
SHA-256 checksum: 5744b34fb020ee8710286ce61a20806f6fc5e73a7b9101f0f65fe88a3b2540f3 Verifying attestations

Release files / asrfront-0.1.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Download URL	asrfront-0.1.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Size	122.2 kB
Tags	CPython 3.10 Linux glibc 2.27+ x86-64 Linux glibc 2.28+ x86-64
SHA-256 checksum How to use checksums	`e0a11a24c09b05d4b71d51f600eec391e5d0e62b18fe8702c448b3fa99611e33`
BLAKE2b-256 checksum How to use checksums	`f482d5735f0bb574d1fb24ec841ec460402ac15306478bad8fe4ddfae2bbba01`
Upload date	Oct 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/sjjeong94/asrfront
Publishing commit: github.com/sjjeong94/asrfront/tree/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59

Workflow

Publishing configuration: github.com/sjjeong94/asrfront/blob/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59/.github/workflows/wheels.yml
Publishing logs: github.com/sjjeong94/asrfront/actions/runs/38024623597/attempts/1

Artifact

Subject: asrfront-0.1.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
SHA-256 checksum: e0a11a24c09b05d4b71d51f600eec391e5d0e62b18fe8702c448b3fa99611e33 Verifying attestations

Release files / asrfront-0.1.0-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl

Download URL	asrfront-0.1.0-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
Size	109.0 kB
Tags	CPython 3.10 Linux glibc 2.26+ ARM64 Linux glibc 2.28+ ARM64
SHA-256 checksum How to use checksums	`4c2bde5b6c4de5975cfd174f35e2e2e5ddcc8d63565864b1b88ab060fb2e1d6b`
BLAKE2b-256 checksum How to use checksums	`f5203390d346b829f4a04fcd91218fb5dce5865b91ab5dc6e56981e3c0332800`
Upload date	Oct 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/sjjeong94/asrfront
Publishing commit: github.com/sjjeong94/asrfront/tree/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59

Workflow

Publishing configuration: github.com/sjjeong94/asrfront/blob/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59/.github/workflows/wheels.yml
Publishing logs: github.com/sjjeong94/asrfront/actions/runs/38024623597/attempts/1

Artifact

Subject: asrfront-0.1.0-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
SHA-256 checksum: 4c2bde5b6c4de5975cfd174f35e2e2e5ddcc8d63565864b1b88ab060fb2e1d6b Verifying attestations

Release files / asrfront-0.1.0-cp39-cp39-win_amd64.whl

Download URL	asrfront-0.1.0-cp39-cp39-win_amd64.whl
Size	96.6 kB
Tags	CPython 3.9 Windows x86-64
SHA-256 checksum How to use checksums	`97f0e5b28532f85f5e42fe53ee204a2a3b26ffe83d20a44d60f5c65dfe5f93f0`
BLAKE2b-256 checksum How to use checksums	`f10e11a807702f25e4a87b9a30d0ff39c53bbefdabb59948f652a1bbb1b9bfe9`
Upload date	Oct 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/sjjeong94/asrfront
Publishing commit: github.com/sjjeong94/asrfront/tree/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59

Workflow

Publishing configuration: github.com/sjjeong94/asrfront/blob/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59/.github/workflows/wheels.yml
Publishing logs: github.com/sjjeong94/asrfront/actions/runs/38024623597/attempts/1

Artifact

Subject: asrfront-0.1.0-cp39-cp39-win_amd64.whl
SHA-256 checksum: 97f0e5b28532f85f5e42fe53ee204a2a3b26ffe83d20a44d60f5c65dfe5f93f0 Verifying attestations

Release files / asrfront-0.1.0-cp39-cp39-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Download URL	asrfront-0.1.0-cp39-cp39-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Size	116.2 kB
Tags	CPython 3.9 Linux glibc 2.27+ x86-64 Linux glibc 2.28+ x86-64
SHA-256 checksum How to use checksums	`48386981898895d93394afaeb90ea343dc4f14eb99c050457a0b8930480d19ec`
BLAKE2b-256 checksum How to use checksums	`6287bcd51964d04cfa60df62b1e887757edc2488da193d19cce01f8604d4b883`
Upload date	Oct 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/sjjeong94/asrfront
Publishing commit: github.com/sjjeong94/asrfront/tree/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59

Workflow

Publishing configuration: github.com/sjjeong94/asrfront/blob/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59/.github/workflows/wheels.yml
Publishing logs: github.com/sjjeong94/asrfront/actions/runs/38024623597/attempts/1

Artifact

Subject: asrfront-0.1.0-cp39-cp39-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
SHA-256 checksum: 48386981898895d93394afaeb90ea343dc4f14eb99c050457a0b8930480d19ec Verifying attestations

Release files / asrfront-0.1.0-cp39-cp39-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl

Download URL	asrfront-0.1.0-cp39-cp39-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
Size	103.2 kB
Tags	CPython 3.9 Linux glibc 2.26+ ARM64 Linux glibc 2.28+ ARM64
SHA-256 checksum How to use checksums	`43de4b40e25727162e45932ac2e51bd533770977dc0ed59994bc0c3c7ab04853`
BLAKE2b-256 checksum How to use checksums	`e1da2d7ac7d6da37e40caa01e57a26e53552a6bf5cafa213971ee9e62a2755a5`
Upload date	Oct 10, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	Yes
Uploaded via	`twine/7.0.0 CPython/3.13.14`

Provenance

Identity

Publishing platform: GitHub Actions
Publishing repository: github.com/sjjeong94/asrfront
Publishing commit: github.com/sjjeong94/asrfront/tree/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59

Workflow

Publishing configuration: github.com/sjjeong94/asrfront/blob/6cd521a1ef4d2e27d6494477966d10b3d9a1bb59/.github/workflows/wheels.yml
Publishing logs: github.com/sjjeong94/asrfront/actions/runs/38024623597/attempts/1

Artifact

Subject: asrfront-0.1.0-cp39-cp39-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
SHA-256 checksum: 43de4b40e25727162e45932ac2e51bd533770977dc0ed59994bc0c3c7ab04853 Verifying attestations

Release history Release notifications | RSS feed

This release

0.1.0 This release

Oct 10, 2026 13 release files

asrfront 0.1.0

asrfront

Install

Usage

Whisper

SenseVoice

Threads

Performance

Accuracy

Development

License

Project links

Key dates

1 maintainer

Credits

GitHub Statistics

License

Requires

Tags

Classifiers

Metadata

Project links

Key dates

1 maintainer

Credits

GitHub Statistics

License

Requires

Tags

Classifiers

Release files for asrfront 0.1.0

Source distribution (sdist)

Built distributions (wheels)

Release files / asrfront-0.1.0.tar.gz

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / asrfront-0.1.0-cp312-abi3-win_amd64.whl

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / asrfront-0.1.0-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / asrfront-0.1.0-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / asrfront-0.1.0-cp311-cp311-win_amd64.whl

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / asrfront-0.1.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / asrfront-0.1.0-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl

Provenance

PyPI Publish Attestation

Identity

Workflow

Artifact

Release files / asrfront-0.1.0-cp310-cp310-win_amd64.whl

Provenance

PyPI Publish Attestation

Identity

Workflow