seprq
SSL speech feature extractors for SepRQ and BEST-RQ (50 Hz). The
encoder (CNN frontend + 12-layer Conformer) and global norm stats are pulled
from the Hugging Face Hub (SevKod/SepRQ)
on first use — only the requested model is downloaded. Upstream
speechbrain>=1.0.3 only; runs on CPU or GPU.
Install
pip install git+https://github.com/SevKod/SepRQ.git # install straight from GitHub
# or, from a local checkout:
pip install .
Use
from seprq import SepRQEncoder
speech_encoder = SepRQEncoder("SepRQ") # or "BestRQ_50Hz"
feats = speech_encoder("utterance.wav") # torch.Tensor [1, T, 576]
Calling the encoder runs forward. It accepts a file path (any
format/sample rate — decoded, downmixed to mono and resampled to 16 kHz for
you) or a raw 1D 16 kHz waveform (numpy array / tensor).
The repo is private, so authenticate once: huggingface-cli login (or set HF_TOKEN).
1 maintainer
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file seprq-0.1.0.tar.gz.
File metadata
- Download URL: seprq-0.1.0.tar.gz
- Upload date:
- Size: 3.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/7.0.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
be68d54fba4b9a2a0a9d7d79162d43d1f74741e8cc52e4b38724c404a6f6f456
|
|
| MD5 |
3bf087056c8d262281450554d2febb53
|
|
| BLAKE2b-256 |
fc903a8e7affea0e013812b7d1cdd3a5ce3f93d561da42acc006cdfd27f6ae86
|
Provenance
The following attestation bundles were made for seprq-0.1.0.tar.gz:
Publisher:
publish.yml on SevKod/SepRQ
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
seprq-0.1.0.tar.gz -
Subject digest:
be68d54fba4b9a2a0a9d7d79162d43d1f74741e8cc52e4b38724c404a6f6f456 - Sigstore transparency entry: 2772950302
- Sigstore integration time:
-
Permalink:
SevKod/SepRQ@1adc2d4c7b476887fd47d6e5aaf9e45540fc1823 -
Branch / Tag:
refs/tags/v0.1.1 - Owner: https://github.com/SevKod
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@1adc2d4c7b476887fd47d6e5aaf9e45540fc1823 -
Trigger Event:
push
-
Statement type:
File details
Details for the file seprq-0.1.0-py3-none-any.whl.
File metadata
- Download URL: seprq-0.1.0-py3-none-any.whl
- Upload date:
- Size: 3.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via:
twine/7.0.0 CPython/3.13.14
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
6aa5c8ecad632698cb20af92e237404ff92cd35724f007a683bd70167b718b83
|
|
| MD5 |
d05368b844bf72720f332879c2717498
|
|
| BLAKE2b-256 |
9e203e1f788766ef7a41e5275ba911ea7cb81cde0b4084264a6793ee07082994
|
Provenance
The following attestation bundles were made for seprq-0.1.0-py3-none-any.whl:
Publisher:
publish.yml on SevKod/SepRQ
-
Statement:
-
Statement type:
https://in-toto.io/Statement/v1 -
Predicate type:
https://docs.pypi.org/attestations/publish/v1 -
Subject name:
seprq-0.1.0-py3-none-any.whl -
Subject digest:
6aa5c8ecad632698cb20af92e237404ff92cd35724f007a683bd70167b718b83 - Sigstore transparency entry: 2772950332
- Sigstore integration time:
-
Permalink:
SevKod/SepRQ@1adc2d4c7b476887fd47d6e5aaf9e45540fc1823 -
Branch / Tag:
refs/tags/v0.1.1 - Owner: https://github.com/SevKod
-
Access:
public
-
Token Issuer:
https://token.actions.githubusercontent.com -
Runner Environment:
github-hosted -
Publication workflow:
publish.yml@1adc2d4c7b476887fd47d6e5aaf9e45540fc1823 -
Trigger Event:
push
-
Statement type:
