Single-instrument to MIDI · TelkNet

MIDI / transcriptionGPU workloadGitHub 2ed0c8349aacc0f88b8ee5b08e6d4794c86454e7

Single-instrument to MIDI

Convert isolated instrument recordings into MIDI for notation and arranging. Choose a model for your source and review its supported instruments.

15 credits/useFile inputMax 100 MBEstimated 20-900 seconds

Input

Supports inputs in formats such as mp3 / wav / flac / ogg / m4a / aac / aif / aiff / mp4 / mov / mkv

Supported formats

mp3wavflacoggm4aaacaifaiffmp4movmkv

Output

MIDI

Use case

Edit notes, instrumentation and performance details.

Choose a model family

Single-instrument to MIDI · SwiftF0AvailableSwiftF0 0.2.0 uses its official pitch tracking and note segmentation for monophonic recordings. Outputs MIDI, frame-level pitch CSV and a plot.Single-instrument recording to MIDI · Basic PitchAvailableSpotify Basic Pitch transcribes polyphonic performances from nearly any instrument, including voice, into MIDI and optional note-event CSV with pitch bends. It works best on one instrument at a time.Single-instrument to MIDI · GAPSAvailableGAPS converts clean or separated solo guitar into note events and MIDI, without string positions, frets, continuous F0 or Pitch Bend. Adjust MIDI velocity by comparing with the original recording.Single-instrument to MIDI · Guitar-FLAvailableGuitar-FL converts guitar solos from the François Leduc data domain into discrete note events and MIDI; FL does not mean frame-level. It does not output continuous F0 or Pitch Bend.Single-instrument to MIDI · FiloSaxAvailableFiloSax targets monophonic jazz saxophone solos and exports discrete pitch, onset, and offset events as MIDI. It does not output continuous pitch, slide, or vibrato tracks.Single-instrument to MIDI · FiloBassAvailableFiloBass targets monophonic jazz double bass (upright bass), not general or electric bass. Use a clean or separated stem; kick and low-frequency bleed can create false notes.Single-instrument to MIDI · VioPTTAvailableVioPTT outputs violin note events and one of four technique labels—détaché, flageolet, spiccato, pizzicato—or none. MIDI velocity is fixed, not measured performance dynamics.STRADIAvailableSTRAdi Offline is the matched non-causal, full-context reference route. It exports the same discrete MIDI and onset, offset and pitch CSV; it is not a published score-following system either.TsumugiAvailableTsumugi · Bass v2: Edit notes, instrumentation and performance details.

Choose by input and output needs, then comparable tests, published evaluations and capabilities. Missing scores do not imply lower quality; more parameters or a newer release do not prove superiority. This is a suggested usage order, not an overall leaderboard.

Cost, time, formats and parameters depend on the selected model.

Models in this field

18 entries

Published results include models on and off this site. The overall ranking opens first; switch the benchmark or category to see its ranking. Each benchmark keeps its own evaluation conditions.

BenchmarkRanking category

Overall rankingHigher is better · best first

Uses the published primary metric for this test; scores are not pooled across benchmarks.

SwiftF0 0.2.0 uses the author's latest pitch-benchmark: 10 corpora, 8 scored conditions and 50 cents tolerance. This is pitch F1; the difference from RMVPE is statistically undetermined. Asymmetric 95% CIs are retained. REAPER is unranked due to incomplete results; the older 0.1.x paper does not score 0.2.0.

Markers identify models or components used here. Scores and settings come from the cited tests, not a new evaluation of the complete site pipeline.

Official pitch-benchmark · fce395c ↗

View chart data

Rank	Model	Pitch F1@50c
1	SwiftF0 0.2.0Used on this site	0.778
2	RMVPE	0.768
3	FCPE	0.728
4	TorchCREPE	0.691
5	CREPE	0.689
6	PESTO	0.68
7	SHS	0.657
8	Praat	0.651
9	RAPT	0.64
10	HarmoF0	0.639
11	SWIPE	0.61
12	SPICE	0.602
13	Harvest	0.6
14	DIO	0.56
14	PENN	0.56
14	YAAPT	0.56
17	Basic Pitch	0.557
18	pYIN	0.506

All original results and sources

Scores apply only to the cited dataset, metric and model version. Leading this table does not mean a current world record or a result from this service. Capabilities and tests can justify prioritizing models without comparable scores.

Benchmark chart: Model comparison

Scores come from the cited public sources; blue rows are models available in this tool.

Instrument-Specific Audio to MIDI

VioPTT paper · Table 1

The sources use different training or task settings, so compare numbers only within the stated protocol.

Public sources checked: 2026-09-10

Test setting	Model	F1 (%)	Detailed metrics
URMP violin tracks · Table 1	VioPTT w/ augmentation (paper)VioPTT paper Table 1	84.50	Precision (%)86.10Recall (%)83.60
Bach10 violin tracks · Table 1	VioPTT w/ augmentation (paper)VioPTT paper Table 1	69.90	Precision (%)68.10Recall (%)71.80

GAPS / Guitar-FL · GuitarSet · zero-shot · 50 ms

GAPS · Table 4

Paper results retain their datasets. FiloBass Table 5 evaluates other algorithms on that dataset; the current FiloBass checkpoint has no published score.

Ranks are computed within each table and evaluation context, retaining ties. Change the metric to reorder; scroll horizontally for every column. Missing values are unranked, never zero.

Public sources checked: 2026-09-23

Rank by metricTest setting

Showing 10/10 rows · 3 metrics

GAPS / Guitar-FL · GuitarSet · zero-shot · 50 ms
Rank	Test setting	Model	Note onset F1 (%)	Precision (%)	Recall (%)
#1	GuitarSet · zero-shot · 50 ms	GAPS (Maman initialization)	88.10	91.10	85.90
#2	GuitarSet · zero-shot · 50 ms	Guitar-FL	87.30	88.00	87.10
#3	GuitarSet · zero-shot · 50 ms	GAPS (Kong initialization)	87.00	91.60	83.70
#4	GuitarSet · zero-shot · 50 ms	GAPS (scratch)	86.10	92.40	81.80
#5	GuitarSet · zero-shot · 50 ms	Maman (MusicNet EM {}_{\textit{EM}} ) [ 1 ]	82.90	86.60	80.40
#6	GuitarSet · zero-shot · 50 ms	Maman (Guitar) [ 1 ]	82.20	86.70	79.70
#7	GuitarSet · zero-shot · 50 ms	Zang et al. [ 8 ] (Synthtab)	70.20	—	—
#8	GuitarSet · zero-shot · 50 ms	Kong et al. [ 10 ]	54.80	67.50	49.70
#9	GuitarSet · zero-shot · 50 ms	Kong et al. (w/ aug)	50.30	80.60	44.00
#10	GuitarSet · zero-shot · 50 ms	MT3 [ 16 ]	32.00	—	—

GAPS / Guitar-FL · FrançoisLeduc test · 50 ms

GAPS · Table 5

Paper results retain their datasets. FiloBass Table 5 evaluates other algorithms on that dataset; the current FiloBass checkpoint has no published score.

Ranks are computed within each table and evaluation context, retaining ties. Change the metric to reorder; scroll horizontally for every column. Missing values are unranked, never zero.

Public sources checked: 2026-09-23

Rank by metricTest setting

Showing 6/6 rows · 3 metrics

GAPS / Guitar-FL · FrançoisLeduc test · 50 ms
Rank	Test setting	Model	Note onset F1 (%)	Precision (%)	Recall (%)
#1	FrançoisLeduc test · 50 ms	GAPS (Maman initialization)	84.80	85.50	84.20
#2	FrançoisLeduc test · 50 ms	Guitar-FL	84.70	83.90	85.50
#3	FrançoisLeduc test · 50 ms	Lu et al. [ 14 ]	80.00	83.60	77.30
#4	FrançoisLeduc test · 50 ms	Omnizart [ 17 ]	67.10	63.00	72.10
#5	FrançoisLeduc test · 50 ms	Basic Pitch [ 15 ]	66.10	54.60	85.00
#6	FrançoisLeduc test · 50 ms	MT3 [ 16 ]	52.40	48.80	57.00

GAPS / Guitar-FL · GAPS test · 50 ms

GAPS · Table 6

Paper results retain their datasets. FiloBass Table 5 evaluates other algorithms on that dataset; the current FiloBass checkpoint has no published score.

Ranks are computed within each table and evaluation context, retaining ties. Change the metric to reorder; scroll horizontally for every column. Missing values are unranked, never zero.

Public sources checked: 2026-09-23

Rank by metricTest setting

Showing 4/4 rows · 3 metrics

GAPS / Guitar-FL · GAPS test · 50 ms
Rank	Test setting	Model	Note onset F1 (%)	Precision (%)	Recall (%)
#1	GAPS test · 50 ms	GAPS (Maman initialization)	94.30	95.00	93.60
#2	GAPS test · 50 ms	GAPS (Kong initialization)	94.00	94.60	93.40
#3	GAPS test · 50 ms	GAPS (scratch)	93.40	94.90	92.10
#4	GAPS test · 50 ms	Guitar-FL	92.10	92.90	91.40

FiloSax · FiloSax · 25-track test · 50 ms

FiloSax · Table 3

Paper results retain their datasets. FiloBass Table 5 evaluates other algorithms on that dataset; the current FiloBass checkpoint has no published score.

Ranks are computed within each table and evaluation context, retaining ties. Change the metric to reorder; scroll horizontally for every column. Missing values are unranked, never zero.

Public sources checked: 2026-09-23

Rank by metricTest setting

Showing 3/3 rows · 3 metrics

FiloSax · FiloSax · 25-track test · 50 ms
Rank	Test setting	Model	Note onset F1 (%)	Precision (%)	Recall (%)
#1	FiloSax · 25-track test · 50 ms	FiloSax	96.19	96.47	95.90
#2	FiloSax · 25-track test · 50 ms	Başaran et al.	90.01	87.68	92.57
#3	FiloSax · 25-track test · 50 ms	CREPE Notes	82.67	82.35	83.05

FiloSax · Omnibook · 50 ms

FiloSax · Table 4

Paper results retain their datasets. FiloBass Table 5 evaluates other algorithms on that dataset; the current FiloBass checkpoint has no published score.

Ranks are computed within each table and evaluation context, retaining ties. Change the metric to reorder; scroll horizontally for every column. Missing values are unranked, never zero.

Public sources checked: 2026-09-23

Rank by metricTest setting

Showing 3/3 rows · 3 metrics

FiloSax · Omnibook · 50 ms
Rank	Test setting	Model	Note onset F1 (%)	Precision (%)	Recall (%)
#1	Omnibook · 50 ms	FiloSax	75.43	74.70	76.96
#2	Omnibook · 50 ms	Başaran et al.	73.68	70.60	77.98
#3	Omnibook · 50 ms	CREPE Notes	70.41	70.93	70.63

FiloBass · dataset baselines

FiloBass dataset paper · Table 5

Paper results retain their datasets. FiloBass Table 5 evaluates other algorithms on that dataset; the current FiloBass checkpoint has no published score.

Ranks are computed within each table and evaluation context, retaining ties. Change the metric to reorder; scroll horizontally for every column. Missing values are unranked, never zero.

Public sources checked: 2026-09-23

± indicates standard deviation.

Rank by metricTest setting

Showing 3/3 rows · 4 metrics

FiloBass · dataset baselines
Rank	Test setting	Model	Note onset F1 (%)	Recall (%)	Precision (%)	Overlap (%)
#1	FiloBass dataset · 50 ms	Melodyne	78.95 ± 15.02	79.52 ± 14.77	78.48 ± 15.41	87.94 ± 3.91
#2	FiloBass dataset · 50 ms	CREPE Notes	72.89 ± 12.68	74.11 ± 12.09	71.81 ± 13.33	78.77 ± 2.68
#3	FiloBass dataset · 50 ms	Basic Pitch	62.73 ± 5.55	81.28 ± 6.26	51.40 ± 6.28	65.24 ± 4.51

SwiftF0 0.2.0 · pitch-benchmark

Official pitch-benchmark · fce395c

Ranks are computed within each table and evaluation context, retaining ties. Change the metric to reorder; scroll horizontally for every column. Missing values are unranked, never zero.

Public sources checked: 2026-09-23

Rank by metricTest setting

Showing 18/18 rows · 4 metrics

SwiftF0 0.2.0 · pitch-benchmark
Rank	Test setting	Model	Pitch F1@50c	Voicing F1	CI95 lo	CI95 hi
#1	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	SwiftF0 0.2.0TelkNet	0.778	0.839	0.765	0.792
#2	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	RMVPE	0.768	0.837	0.752	0.783
#3	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	FCPE	0.728	0.812	0.712	0.742
#4	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	TorchCREPE	0.691	0.761	0.673	0.706
#5	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	CREPE	0.689	0.781	0.672	0.704
#6	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	PESTO	0.680	0.850	0.663	0.697
#7	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	SHS	0.657	0.773	0.640	0.672
#8	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	Praat	0.651	0.815	0.634	0.667
#9	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	RAPT	0.640	0.799	0.621	0.655
#10	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	HarmoF0	0.639	0.727	0.622	0.653
#11	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	SWIPE	0.610	0.761	0.589	0.624
#12	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	SPICE	0.602	0.751	0.582	0.619
#13	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	Harvest	0.600	0.782	0.584	0.614
#14	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	YAAPT	0.560	0.842	0.539	0.580
#14	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	PENN	0.560	0.720	0.539	0.579
#14	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	DIO	0.560	0.710	0.541	0.577
#17	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	Basic Pitch	0.557	0.775	0.539	0.573
#18	pitch-benchmark · 10 corpora · 8 altered conditions · 50 cents	pYIN	0.506	0.656	0.482	0.525

Basic Pitch NMP published per-dataset scores (paper Table 2)

Basic Pitch paper, Table 2

Scores come from the linked base checkpoint, not a new measurement of the model running here.

Public sources checked: 2026-09-10

Dataset	Model	F_no-offset	Detailed metrics
Molina	NMPPaper Table 2	0.52	Frame accuracy ↑0.63F_with-offset ↑0.35
GuitarSet	NMPPaper Table 2	0.79	Frame accuracy ↑0.70F_with-offset ↑0.56
MAESTRO	NMPPaper Table 2	0.71	Frame accuracy ↑0.38F_with-offset ↑0.11
Slakh	NMPPaper Table 2	0.42	Frame accuracy ↑0.44F_with-offset ↑0.21
PHENICX	NMPPaper Table 2	0.49	Frame accuracy ↑0.53F_with-offset ↑0.35

Tsumugi · other

Tsumugi · pinned README · other

Tsumugi Other and Vocal Harmony report COnP, not COnF1. Published results cover v1.5; default Vocal Harmony v1.6 has no published score. Instrument refinement remains experimental, with datasets shown separately.

Ranks are computed within each table and evaluation context, retaining ties. Change the metric to reorder; scroll horizontally for every column. Missing values are unranked, never zero.

Public sources checked: 2026-09-23

Rank by metricTest setting

Showing 2/2 rows · 1 metrics

Tsumugi · other
Rank	Test setting	Model	COnP (%)
#1	In-house real audio	other_v1_5	77.01
#2	In-house real audio	other	73.18

Tsumugi · vocal harmony v1.5

Tsumugi · pinned README · harmony

Ranks are computed within each table and evaluation context, retaining ties. Change the metric to reorder; scroll horizontally for every column. Missing values are unranked, never zero.

Public sources checked: 2026-09-23

Rank by metricTest setting

Showing 2/2 rows · 1 metrics

Tsumugi · vocal harmony v1.5
Rank	Test setting	Model	COnP (%)
#1	Held-out MIR-ST500	vocal_harmony_v1_5	68.14
#2	Held-out MIR-ST500	vocal_harmony	60.52

Tsumugi · drums v1.5

Tsumugi · pinned README · drums

Ranks are computed within each table and evaluation context, retaining ties. Change the metric to reorder; scroll horizontally for every column. Missing values are unranked, never zero.

Public sources checked: 2026-09-23

Rank by metricTest setting

Showing 2/2 rows · 2 metrics

Tsumugi · drums v1.5
Rank	Test setting	Model	DrumKit F1 (%)	AllPercussion F1 (%)
#1	Audio-aligned · 50 ms · canonical GM	drums_v1_5	68.90	40.44
#2	Audio-aligned · 50 ms · canonical GM	drums	61.57	18.79

Tsumugi · instrument refinement

Tsumugi · pinned README · RWC-I

Ranks are computed within each table and evaluation context, retaining ties. Change the metric to reorder; scroll horizontally for every column. Missing values are unranked, never zero.

Public sources checked: 2026-09-23

Rank by metricTest setting

Showing 2/2 rows · 1 metrics

Tsumugi · instrument refinement
Rank	Test setting	Model	ACC (%)
#1	Held-out RWC-I	Instrument refinement model	74.50
#2	Held-out RWC-I	Base instrument classifier	71.30

Models, parameters, and sources

SwiftF0 0.2.0 uses its official pitch tracking and note segmentation for monophonic recordings. Outputs MIDI, frame-level pitch CSV and a plot.

SwiftF0SwiftF0 0.2.0 sourceSwiftF0 paperVioPTT paper · Table 1VioPTT w/ augmentation (paper)URMP violin tracks · Table 1VioPTT paper Table 1Bach10 violin tracks · Table 1GAPS · Table 4MT3 [ 16 ]GuitarSet · zero-shot · 50 msKong et al. [ 10 ]

SwiftF0

SwiftF0 0.2.0 source SwiftF0 paper

SwiftF0 0.2.0 uses the author's latest pitch-benchmark: 10 corpora, 8 scored conditions and 50 cents tolerance. This is pitch F1; the difference from RMVPE is statistically undetermined. Asymmetric 95% CIs are retained. REAPER is unranked due to incomplete results; the older 0.1.x paper does not score 0.2.0.

Basic Pitch

Spotify Basic Pitch transcribes polyphonic performances from nearly any instrument, including voice, into MIDI and optional note-event CSV with pitch bends. It works best on one instrument at a time.

Basic Pitch source and weights (pinned)ICASSP 2022 paper

Basic Pitch onset confidence threshold.
Basic Pitch frame-level activation threshold.
Shortest note retained by Basic Pitch, in milliseconds.
Discard Basic Pitch notes below this frequency; leave blank for no limit.
Discard Basic Pitch notes above this frequency; leave blank for no limit.
Keep separate pitch-bend curves for simultaneous Basic Pitch notes.
Enable Basic Pitch’s official Melodia-inspired post-processing.
After inference, Beat This final0 writes a valid fixed tempo or beat-by-beat tempo map into the MIDI while preserving every event's position in seconds. If valid beat evidence cannot be produced, the task fails instead of delivering MIDI with the model's default tempo.

GAPS

GAPS converts clean or separated solo guitar into note events and MIDI, without string positions, frets, continuous F0 or Pitch Bend. Adjust MIDI velocity by comparing with the original recording.

GAPS runtime (pinned)GAPS weights (pinned)ISMIR 2024 paper

Paper results retain their datasets. FiloBass Table 5 evaluates other algorithms on that dataset; the current FiloBass checkpoint has no published score.

Guitar-FL

Guitar-FL converts guitar solos from the François Leduc data domain into discrete note events and MIDI; FL does not mean frame-level. It does not output continuous F0 or Pitch Bend.

Guitar-FL runtime (pinned)Guitar-FL weights (pinned)Guitar-FL paper Pinned Guitar-FL technical guide

Paper results retain their datasets. FiloBass Table 5 evaluates other algorithms on that dataset; the current FiloBass checkpoint has no published score.

FiloSax

FiloSax targets monophonic jazz saxophone solos and exports discrete pitch, onset, and offset events as MIDI. It does not output continuous pitch, slide, or vibrato tracks.

FiloSax runtime (pinned)FiloSax weights (pinned)FiloSax pipeline paper

Paper results retain their datasets. FiloBass Table 5 evaluates other algorithms on that dataset; the current FiloBass checkpoint has no published score.

FiloBass

FiloBass targets monophonic jazz double bass (upright bass), not general or electric bass. Use a clean or separated stem; kick and low-frequency bleed can create false notes.

FiloBass runtime (pinned)FiloBass weights (pinned)FiloBass paper

Paper results retain their datasets. FiloBass Table 5 evaluates other algorithms on that dataset; the current FiloBass checkpoint has no published score.

VioPTT

VioPTT outputs violin note events and one of four technique labels—détaché, flageolet, spiccato, pizzicato—or none. MIDI velocity is fixed, not measured performance dynamics.

VioPTT source VioPTT paper

Separate first: split vocals/accompaniment or stems before transcribing the target audio.
Select the released checkpoint that matches the source stem; this is routing, not automatic instrument recognition.

STrADi · Offline

STRAdi Offline is the matched non-causal, full-context reference route. It exports the same discrete MIDI and onset, offset and pitch CSV; it is not a published score-following system either.

STRAdi source (pinned)STRAdi v1.0.0 offline checkpoint STRAdi ISMIR 2026 technical page

Separate first: split vocals/accompaniment or stems before transcribing the target audio.
Select the released checkpoint that matches the source stem; this is routing, not automatic instrument recognition.

STrADi · Online

STRAdi Online targets clean solo violin with fully causal inference and no future context. It exports discrete MIDI plus onset, offset and pitch CSV; the public repository does not ship a score-following system.

STRAdi source (pinned)STRAdi v1.0.0 online checkpoint STRAdi ISMIR 2026 technical page

Separate first: split vocals/accompaniment or stems before transcribing the target audio.
Select the released checkpoint that matches the source stem; this is routing, not automatic instrument recognition.

Tsumugi · Bass v2

Tsumugi · Bass v2: Edit notes, instrumentation and performance details.

Instrument-Agnostic AMT source (pinned)Released checkpoints (pinned)Pinned Instrument-Agnostic AMT technical guide

Tsumugi · Guitar v1.5

Tsumugi · Guitar v1.5: Edit notes, instrumentation and performance details.

Instrument-Agnostic AMT source (pinned)Released checkpoints (pinned)Pinned Instrument-Agnostic AMT technical guide

Tsumugi · Other v1.5

Tsumugi · Other v1.5: Edit notes, instrumentation and performance details.

Instrument-Agnostic AMT source (pinned)Released checkpoints (pinned)Pinned Instrument-Agnostic AMT technical guide

Tsumugi · Vocal

Tsumugi · Vocal: Edit notes, instrumentation and performance details.

Instrument-Agnostic AMT source (pinned)Released checkpoints (pinned)Pinned Instrument-Agnostic AMT technical guide

Tsumugi · Vocal Harmony v1.6

Tsumugi · Vocal Harmony v1.6: Edit notes, instrumentation and performance details.

Instrument-Agnostic AMT source (pinned)Released checkpoints (pinned)Pinned Instrument-Agnostic AMT technical guide

Tsumugi · Vocal Harmony v1.5

Tsumugi · Vocal Harmony v1.5: Edit notes, instrumentation and performance details.

Instrument-Agnostic AMT source (pinned)Released checkpoints (pinned)Pinned Instrument-Agnostic AMT technical guide

Tsumugi · Drums v1.5

Tsumugi · Drums v1.5: Edit notes, instrumentation and performance details.

Instrument-Agnostic AMT source (pinned)Released checkpoints (pinned)Pinned Instrument-Agnostic AMT technical guide

Model comparison

Model

Role

Why it is used

Output impact

Paper and benchmark notes

GAPS: A Large and Diverse Classical Guitar Dataset and Benchmark Transcription Model

ISMIR - 2024

GAPS converts clean or separated solo guitar into note events and MIDI, without string positions, frets, continuous F0 or Pitch Bend. Adjust MIDI velocity by comparing with the original recording.

Paper

High Resolution Guitar Transcription via Domain Adaptation

ICASSP - 2024

Guitar-FL converts guitar solos from the François Leduc data domain into discrete note events and MIDI; FL does not mean frame-level. It does not output continuous F0 or Pitch Bend.

Paper

Reconstructing the Charlie Parker Omnibook using an audio-to-score automatic transcription pipeline

SMC - 2024

FiloSax targets monophonic jazz saxophone solos and exports discrete pitch, onset, and offset events as MIDI. It does not output continuous pitch, slide, or vibrato tracks.

Paper

FiloBass: A Dataset and Corpus Based Study of Jazz Basslines

ISMIR - 2023

FiloBass targets monophonic jazz double bass (upright bass), not general or electric bass. Use a clean or separated stem; kick and low-frequency bleed can create false notes.

Paper

VioPTT: Violin Playing Technique-Aware Transcription from Synthetic Data Augmentation

ICASSP - 2026

VioPTT outputs violin note events and one of four technique labels—détaché, flageolet, spiccato, pizzicato—or none. MIDI velocity is fixed, not measured performance dynamics.

Paper Project page

SwiftF0: Fast and Accurate Monophonic Pitch Detection

arXiv - 2025

Paper

A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation

ICASSP - 2022

Spotify Basic Pitch transcribes polyphonic performances from nearly any instrument, including voice, into MIDI and optional note-event CSV with pitch bends. It works best on one instrument at a time.

Paper

Instrument-Agnostic AMT: released checkpoints and inference guide

Official technical guide - 2026

Convert isolated instrument, vocal or drum tracks to MIDI using the matching official model. Vocal harmony also supports the v1.6 checkpoint. Instrument label refinement remains experimental.

Pinned technical guide

Parameter guide

SwiftF0 0.2.0 uses the author's latest pitch-benchmark: 10 corpora, 8 scored conditions and 50 cents tolerance. This is pitch F1; the difference from RMVPE is statistically undetermined. Asymmetric 95% CIs are retained. REAPER is unranked due to incomplete results; the older 0.1.x paper does not score 0.2.0.

Workflow

1Upload a single-instrument recording and select its specialist model.
2Import the MIDI into a DAW to review pitches, onsets and note lengths.

Before you submit

Select the released checkpoint that matches the source stem; this is routing, not automatic instrument recognition.
If other instruments are mixed in, separate them first before transcribing

Quick feedback

Include the tool name, steps and the problem in your feedback. Screenshots can help us locate it.

Single-instrument to MIDI

Models in this field

Benchmark chart: Model comparison

Instrument-Specific Audio to MIDI

GAPS / Guitar-FL · GuitarSet · zero-shot · 50 ms

GAPS / Guitar-FL · FrançoisLeduc test · 50 ms

GAPS / Guitar-FL · GAPS test · 50 ms

FiloSax · FiloSax · 25-track test · 50 ms

FiloSax · Omnibook · 50 ms

FiloBass · dataset baselines

SwiftF0 0.2.0 · pitch-benchmark

Basic Pitch NMP published per-dataset scores (paper Table 2)

Tsumugi · other

Tsumugi · vocal harmony v1.5

Tsumugi · drums v1.5

Tsumugi · instrument refinement

Models, parameters, and sources

SwiftF0

Basic Pitch

GAPS

Guitar-FL

FiloSax

FiloBass

VioPTT

STrADi · Offline

STrADi · Online

Tsumugi · Bass v2

Tsumugi · Guitar v1.5

Tsumugi · Other v1.5

Tsumugi · Vocal

Tsumugi · Vocal Harmony v1.6

Tsumugi · Vocal Harmony v1.5

Tsumugi · Drums v1.5

Model comparison

Paper and benchmark notes

GAPS: A Large and Diverse Classical Guitar Dataset and Benchmark Transcription Model

High Resolution Guitar Transcription via Domain Adaptation

Reconstructing the Charlie Parker Omnibook using an audio-to-score automatic transcription pipeline

FiloBass: A Dataset and Corpus Based Study of Jazz Basslines

VioPTT: Violin Playing Technique-Aware Transcription from Synthetic Data Augmentation

SwiftF0: Fast and Accurate Monophonic Pitch Detection

A Lightweight Instrument-Agnostic Model for Polyphonic Note Transcription and Multipitch Estimation

Instrument-Agnostic AMT: released checkpoints and inference guide

Official / repositories

Papers / technical notes

Parameter guide

Workflow

Before you submit

Quick feedback