Downloads · 30 days
451
100% of all-time downloads
cstr/basic-pitch-GGUF
basic-pitch-GGUF is a audio classification model from cstr. Use it for the audio classification task on the model card, and read the license before you ship it in a product. It is set up for ggml. The card lists the license as apache-2.0.
GGUF / ggml conversion of Spotify Basic Pitch (ICASSP 2022 nmp model, Apache-2.0) for CrispStrobe/CrispASR (§250): lightweight polyphonic audio → note-event transcription (any instrument, 88-key MIDI range).
Downloads · 30 days
451
100% of all-time downloads
All-time downloads
451
Public
Repo size
258 KB
Likes
0
Public
Click a slice to open those files.
.gguf258 KB · 99%
From the Hugging Face model README
GGUF / ggml conversion of Spotify Basic Pitch (ICASSP 2022 nmp model, Apache-2.0) for CrispStrobe/CrispASR (§250): lightweight polyphonic audio → note-event transcription (any instrument, 88-key MIDI range).
Converted from the nmp.onnx that ships inside the basic-pitch repo (sha256 2c3c1d14…, 230 KB) with models/convert-basic-pitch-to-gguf.py. The nnAudio CQT2010v2 kernels, the 256-tap decimation FIR, and the rescale vector are copied bit-for-bit from the ONNX initializers — nothing DSP-critical is reimplemented.
| File | Size | Notes |
|---|---|---|
basic-pitch-f32.gguf | 146 KB | exact — note events match the Python reference 27/27 and 11/11 on the validation clips |
basic-pitch-f16.gguf | 113 KB | default; two note ends may shift by one frame (11.6 ms) at threshold boundaries |
crispasr --piano --backend basic-pitch -m auto --auto-download -f input.wav
crispasr --piano -m basic-pitch-f32.gguf -f input.wav --piano-format json
Parity vs the upstream ONNX (per-stage cosine ≥ 0.9991 on real audio, 1.000000 on native-rate input; end-to-end note events exact at F32) is enforced by the crispasr-diff basic-pitch harness with tools/reference_backends/basic_pitch.py as the oracle.