Skip to main content

pyannoteAudio modelLimited access

pyannote Community-1

PopularityTop group about equally popular, 8 models

47out of 100new calculation

based on two data groups, mostly search, range 27 to 66

Summary

pyannote Community-1 is a local pipeline for speaker diarization and exclusive diarization. It expects mono audio at 16 kHz and returns speaker segments, not transcription or spoken output.

Hugging Face requires contact information and acceptance of the terms before download. That access gate remains in place even though the pipeline can run locally under CC-BY-4.0.

GraduallyBench Audio

pyannote Community-1

Technical test
  • Only a technical test is available.
  • The selection of test inputs is limited.
  • The technical diarization pretest uses synthetic whole-clip speaker boundaries and is not a comparable DER benchmark.
Show test details

Technical measurement

Local · German, English

Execution CPU. Precision not documented.

8 valid outputs from 8 attempted and 8 planned test slots.

Diarization, technical pretest
15.79 %(67.32 / 426.42 seconds reference speaker time)German, English

WER compares words and CER compares characters with the reference. The speech output was re-transcribed with GPT Transcribe. Its exact backend revision is unconfirmed. Read speech and digital silence do not cover spontaneous speech or real background noise. Error rates can exceed 100 %. Where used, the test references were not independently reviewed by humans. Test coverage and methods differ by model. Each metric stands on its own; there is no combined overall score across tests. Data compiled on 11/10/2026. How we test · Download all Decision and Audio results as JSON

All benchmark results

Every published result with its source, test setup and comparison models.

Show all 79 published benchmark results

Page 1 of 7

Measurements without matching peer values

These measurements have no matching peer values under the same test conditions. Their original values and sources remain available here.

Raven CALLHOME-de DER (collar 0.0) (Show measurement, test conditions, and source)
Source value
20.5767820718
Metric
diarization error rate (DER), corpus-aggregated
Unit
%
Benchmark version
raven.eval run 2026-07-31-callhome-de; published at results-2026-10-02, commit c3c21c94ec9bd127651643af047fbbe3b42528c6
Category
speaker-diarization
Direction
Lower is better
Sample
120
Source type
vendor-reported
Evaluator
Raven raven.eval
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. German telephone diarization on talkbank/callhome config deu (CALLHOME-de), 120 files. Exact model pyannote/speaker-diarization-community-1 at revision 3533c8cf8e369892e6b79ff1bf80f7b0286a54ee; dataset revision 17c8a153215aa7c50b805078fd6284ba81c2fc47. Collar 0.0 s, skip_overlap=false, corpus aggregation, automatic VAD, Hungarian speaker mapping, primary scorer pyannote.metrics. This is the full-collar Raven metric variant, not the NIST/CALLHOME classic variant.
Context
Raven sells meeting transcription and identifies this pyannote model as built into its product. Treat this as a vendor-reported, reproducible public-data result, not an independent evaluation.
Source Raven raven.eval
Raven CALLHOME-de DER (collar 0.25) (Show measurement, test conditions, and source)
Source value
16.0778669871
Metric
diarization error rate (DER), corpus-aggregated
Unit
%
Benchmark version
raven.eval run 2026-07-31-callhome-de; published at results-2026-10-02, commit c3c21c94ec9bd127651643af047fbbe3b42528c6
Category
speaker-diarization
Direction
Lower is better
Sample
120
Lower confidence bound
14.97
Upper confidence bound
17.27
Source type
vendor-reported
Evaluator
Raven raven.eval
Status
active
Retrieved at
2026-10-17
Methodology
Vendor-reported result. German telephone diarization on talkbank/callhome config deu (CALLHOME-de), 120 files. Exact model pyannote/speaker-diarization-community-1 at revision 3533c8cf8e369892e6b79ff1bf80f7b0286a54ee; dataset revision 17c8a153215aa7c50b805078fd6284ba81c2fc47. Collar 0.25 s, skip_overlap=false, corpus aggregation, automatic VAD, Hungarian speaker mapping, primary scorer pyannote.metrics. The report publishes a 95% percentile-bootstrap CI over files, 10,000 resamples, seed 20260903. This is the NIST/CALLHOME classic metric variant, distinct from the 0.0 s collar row.
Context
Raven sells meeting transcription and identifies this pyannote model as built into its product. Treat this as a vendor-reported, reproducible public-data result, not an independent evaluation.
Source Raven raven.eval
Raven VoxConverse dev corpus DER, collar 0.0 s (Show measurement, test conditions, and source)
Source value
7.17
Metric
Diarization error rate (DER), collar 0.0 s, overlap not skipped; lower is better
Unit
%
Benchmark version
Raven run 2026-07-30; dataset labels commit 24bf60be
Direction
Lower is better
Sample
216
Source type
independent-evaluator
Evaluator
Raven evaluator, pinned VoxConverse diarization benchmark results
Status
active
Retrieved at
2026-10-17
Methodology
Independent evaluation. Raven evaluator run dated 2026-07-30, exact model pyannote/speaker-diarization-community-1 at checkpoint 3533c8cf8e369892e6b79ff1bf80f7b0286a54ee; VoxConverse dev split, N=216 files, dataset labels pinned at commit 24bf60be. Corpus-aggregated DER with automatic VAD, Hungarian speaker mapping, overlap not skipped, pyannote.metrics. The config uses 10,000 file-bootstrap resamples, seed 20260903, and 95% confidence. No explicit UEM is declared.
Context
The configuration does not declare an explicit UEM. Its bootstrap confidence interval applies only to the 0.25 s collar result; no interval is assigned to the 0.0 s row. This is a different corpus split and evaluator run from the existing VoxConverse test-set result.
Source Raven evaluator, pinned VoxConverse diarization benchmark results
Raven VoxConverse dev corpus DER, collar 0.25 s (Show measurement, test conditions, and source)
Source value
5
Metric
Diarization error rate (DER), collar 0.25 s, overlap not skipped; lower is better
Unit
%
Benchmark version
Raven run 2026-07-30; dataset labels commit 24bf60be
Direction
Lower is better
Sample
216
Lower confidence bound
4.37
Upper confidence bound
5.7
Source type
independent-evaluator
Evaluator
Raven evaluator, pinned VoxConverse diarization benchmark results
Status
active
Retrieved at
2026-10-17
Methodology
Independent evaluation. Raven evaluator run dated 2026-07-30, exact model pyannote/speaker-diarization-community-1 at checkpoint 3533c8cf8e369892e6b79ff1bf80f7b0286a54ee; VoxConverse dev split, N=216 files, dataset labels pinned at commit 24bf60be. Corpus-aggregated DER with automatic VAD, Hungarian speaker mapping, overlap not skipped, pyannote.metrics. The config uses 10,000 file-bootstrap resamples, seed 20260903, and 95% confidence. No explicit UEM is declared.
Context
The configuration does not declare an explicit UEM. Its bootstrap confidence interval applies only to the 0.25 s collar result; no interval is assigned to the 0.0 s row. This is a different corpus split and evaluator run from the existing VoxConverse test-set result.
Source Raven evaluator, pinned VoxConverse diarization benchmark results
LinTO ETAPE diarization error rate, given speaker count (Show measurement, test conditions, and source)
Source value
28.76
Metric
diarization error rate (DER), lower is better
Unit
%
Benchmark version
Linagora benchmark README at commit 5b4b4734e26cdafdbd482cd536e1e0fa0d87d188, commit dated 2026-10-09; run date not stated
Category
audio
Direction
Lower is better
Source type
vendor-reported
Evaluator
Linagora Labs, LinTO speaker diarization benchmark
Status
active
Retrieved at
2026-10-18
Methodology
Vendor-reported result. LinTO diarization system linto-pyannote 2.3.0 with pyannote.audio 4 community-1; ETAPE; DER with a given number of speakers; the source notes re-clustering with KMeans when the supplied speaker count differs from VBx. Run date, cell denominator, and confidence interval are not stated.
Context
Vendor-reported by Linagora/LinTO; this is the full LinTO integration, not standalone pyannote quality. The pinned source explicitly maps its linto-pyannote 2.3.0 row to pyannote.audio 4 community-1. The benchmark run date, per-cell sample count, and confidence interval are not stated.
Source Linagora Labs, LinTO speaker diarization benchmark
LinTO ETAPE diarization error rate, unknown speaker count (Show measurement, test conditions, and source)
Source value
12.8
Metric
diarization error rate (DER), lower is better
Unit
%
Benchmark version
Linagora benchmark README at commit 5b4b4734e26cdafdbd482cd536e1e0fa0d87d188, commit dated 2026-10-09; run date not stated
Category
audio
Direction
Lower is better
Source type
vendor-reported
Evaluator
Linagora Labs, LinTO speaker diarization benchmark
Status
active
Retrieved at
2026-10-18
Methodology
Vendor-reported result. LinTO diarization system linto-pyannote 2.3.0 with pyannote.audio 4 community-1; ETAPE; DER with an unknown number of speakers; the source notes re-clustering with KMeans when the supplied speaker count differs from VBx. Run date, cell denominator, and confidence interval are not stated.
Context
Vendor-reported by Linagora/LinTO; this is the full LinTO integration, not standalone pyannote quality. The pinned source explicitly maps its linto-pyannote 2.3.0 row to pyannote.audio 4 community-1. The benchmark run date, per-cell sample count, and confidence interval are not stated.
Source Linagora Labs, LinTO speaker diarization benchmark
LinTO LINAGORA diarization error rate, given speaker count (Show measurement, test conditions, and source)
Source value
42.5
Metric
diarization error rate (DER), lower is better
Unit
%
Benchmark version
Linagora benchmark README at commit 5b4b4734e26cdafdbd482cd536e1e0fa0d87d188, commit dated 2026-10-09; run date not stated
Category
audio
Direction
Lower is better
Source type
vendor-reported
Evaluator
Linagora Labs, LinTO speaker diarization benchmark
Status
active
Retrieved at
2026-10-18
Methodology
Vendor-reported result. LinTO diarization system linto-pyannote 2.3.0 with pyannote.audio 4 community-1; LINAGORA; DER with a given number of speakers; the source notes re-clustering with KMeans when the supplied speaker count differs from VBx. Run date, cell denominator, and confidence interval are not stated.
Context
Vendor-reported by Linagora/LinTO; this is the full LinTO integration, not standalone pyannote quality. The pinned source explicitly maps its linto-pyannote 2.3.0 row to pyannote.audio 4 community-1. The benchmark run date, per-cell sample count, and confidence interval are not stated.
Source Linagora Labs, LinTO speaker diarization benchmark
LinTO LINAGORA diarization error rate, unknown speaker count (Show measurement, test conditions, and source)
Source value
29.49
Metric
diarization error rate (DER), lower is better
Unit
%
Benchmark version
Linagora benchmark README at commit 5b4b4734e26cdafdbd482cd536e1e0fa0d87d188, commit dated 2026-10-09; run date not stated
Category
audio
Direction
Lower is better
Source type
vendor-reported
Evaluator
Linagora Labs, LinTO speaker diarization benchmark
Status
active
Retrieved at
2026-10-18
Methodology
Vendor-reported result. LinTO diarization system linto-pyannote 2.3.0 with pyannote.audio 4 community-1; LINAGORA; DER with an unknown number of speakers; the source notes re-clustering with KMeans when the supplied speaker count differs from VBx. Run date, cell denominator, and confidence interval are not stated.
Context
Vendor-reported by Linagora/LinTO; this is the full LinTO integration, not standalone pyannote quality. The pinned source explicitly maps its linto-pyannote 2.3.0 row to pyannote.audio 4 community-1. The benchmark run date, per-cell sample count, and confidence interval are not stated.
Source Linagora Labs, LinTO speaker diarization benchmark
LinTO SUMM-RE diarization error rate, given speaker count (Show measurement, test conditions, and source)
Source value
29.41
Metric
diarization error rate (DER), lower is better
Unit
%
Benchmark version
Linagora benchmark README at commit 5b4b4734e26cdafdbd482cd536e1e0fa0d87d188, commit dated 2026-10-09; run date not stated
Category
audio
Direction
Lower is better
Source type
vendor-reported
Evaluator
Linagora Labs, LinTO speaker diarization benchmark
Status
active
Retrieved at
2026-10-18
Methodology
Vendor-reported result. LinTO diarization system linto-pyannote 2.3.0 with pyannote.audio 4 community-1; SUMM-RE; DER with a given number of speakers; the source notes re-clustering with KMeans when the supplied speaker count differs from VBx. Run date, cell denominator, and confidence interval are not stated.
Context
Vendor-reported by Linagora/LinTO; this is the full LinTO integration, not standalone pyannote quality. The pinned source explicitly maps its linto-pyannote 2.3.0 row to pyannote.audio 4 community-1. The benchmark run date, per-cell sample count, and confidence interval are not stated.
Source Linagora Labs, LinTO speaker diarization benchmark
LinTO SUMM-RE diarization error rate, unknown speaker count (Show measurement, test conditions, and source)
Source value
28.88
Metric
diarization error rate (DER), lower is better
Unit
%
Benchmark version
Linagora benchmark README at commit 5b4b4734e26cdafdbd482cd536e1e0fa0d87d188, commit dated 2026-10-09; run date not stated
Category
audio
Direction
Lower is better
Source type
vendor-reported
Evaluator
Linagora Labs, LinTO speaker diarization benchmark
Status
active
Retrieved at
2026-10-18
Methodology
Vendor-reported result. LinTO diarization system linto-pyannote 2.3.0 with pyannote.audio 4 community-1; SUMM-RE; DER with an unknown number of speakers; the source notes re-clustering with KMeans when the supplied speaker count differs from VBx. Run date, cell denominator, and confidence interval are not stated.
Context
Vendor-reported by Linagora/LinTO; this is the full LinTO integration, not standalone pyannote quality. The pinned source explicitly maps its linto-pyannote 2.3.0 row to pyannote.audio 4 community-1. The benchmark run date, per-cell sample count, and confidence interval are not stated.
Source Linagora Labs, LinTO speaker diarization benchmark
LinTO Simsamu diarization error rate, given speaker count (Show measurement, test conditions, and source)
Source value
18.38
Metric
diarization error rate (DER), lower is better
Unit
%
Benchmark version
Linagora benchmark README at commit 5b4b4734e26cdafdbd482cd536e1e0fa0d87d188, commit dated 2026-10-09; run date not stated
Category
audio
Direction
Lower is better
Source type
vendor-reported
Evaluator
Linagora Labs, LinTO speaker diarization benchmark
Status
active
Retrieved at
2026-10-18
Methodology
Vendor-reported result. LinTO diarization system linto-pyannote 2.3.0 with pyannote.audio 4 community-1; Simsamu; DER with a given number of speakers; the source notes re-clustering with KMeans when the supplied speaker count differs from VBx. Run date, cell denominator, and confidence interval are not stated.
Context
Vendor-reported by Linagora/LinTO; this is the full LinTO integration, not standalone pyannote quality. The pinned source explicitly maps its linto-pyannote 2.3.0 row to pyannote.audio 4 community-1. The benchmark run date, per-cell sample count, and confidence interval are not stated.
Source Linagora Labs, LinTO speaker diarization benchmark
LinTO Simsamu diarization error rate, unknown speaker count (Show measurement, test conditions, and source)
Source value
19.25
Metric
diarization error rate (DER), lower is better
Unit
%
Benchmark version
Linagora benchmark README at commit 5b4b4734e26cdafdbd482cd536e1e0fa0d87d188, commit dated 2026-10-09; run date not stated
Category
audio
Direction
Lower is better
Source type
vendor-reported
Evaluator
Linagora Labs, LinTO speaker diarization benchmark
Status
active
Retrieved at
2026-10-18
Methodology
Vendor-reported result. LinTO diarization system linto-pyannote 2.3.0 with pyannote.audio 4 community-1; Simsamu; DER with an unknown number of speakers; the source notes re-clustering with KMeans when the supplied speaker count differs from VBx. Run date, cell denominator, and confidence interval are not stated.
Context
Vendor-reported by Linagora/LinTO; this is the full LinTO integration, not standalone pyannote quality. The pinned source explicitly maps its linto-pyannote 2.3.0 row to pyannote.audio 4 community-1. The benchmark run date, per-cell sample count, and confidence interval are not stated.
Source Linagora Labs, LinTO speaker diarization benchmark

Page 1 of 7

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

0 to 100, higher is more popular

20 of 54 models

As of November 2026 · Source: gradually.ai popularity index

Over time

Weekly values from October 18, 2026 to November 20, 2026

pyannote Community-1NVIDIA Nemotron 3.5 Transcribe 49Lyria 3.5 47Gemini 3.5 Live Translate 46Granite Speech 5.0 470M TurboCTC NC 45

Method changes in the timeline, a jump at these points is no market event:

  1. 1November 1, 2026: Value only with search or usage data, 30-day attention
  2. 2November 1, 2026: Method version 4 (common scale, shrinkage)
  3. 3November 9, 2026: New topics measurement V20 (daily quorum, short forms)

What is gaining popularity right now, across models, vendors, harnesses and AI subscriptions, is collected in All AI trends.

All specifications

Architecture

Model class
Speaker diarization pipeline
Source: Model class
Checkpoint
pyannote/speaker-diarization-community-1
Source: Checkpoint

Input and output

Input
Mono audio at 16 kHz
Source: Input
Output
Speaker segments and exclusive diarization
Source: Output

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking
Unknown
no source
Watermarking technique
Not known
no source

Licence and access

Access
Local pipeline with an access gate
Source: Access
License
CC-BY-4.0
Source: License
Shutdown
None announced
no source

Further details

Access gate
Hugging Face contact information and terms must be accepted before download
Source: Access gate
Pipeline
Local pyannote.audio pipeline; no Inference Provider entry
Source: Pipeline
Audio format
Mono, 16 kHz
Source: Audio format

Sources and data date

Show all 21 sources

Benchmark sources at a glance

Which independent evaluators tested this model. This is coverage, not a quality ranking.

No active result from the reviewed external evaluators can currently be attributed to this model. Other source evidence remains available below.

Without vendor claims and historical or disputed results; those stay labelled in the single values.

TypeEvidence and data date
Research statusResearch date October 4, 2026. 15 source URLs checked. This documents the inspected sources, not an exhaustive inventory of every publication.
Additional sourcepyannote Community-1 model card (retrieved October 3, 2026; October 4, 2026) · pyannote Community-1 model card · Editorial description reviewed October 3, 2026
Additional sourceRaven raven.eval (retrieved October 17, 2026)
Additional sourcepyannote.audio official benchmark table (retrieved October 17, 2026)
Additional sourceRaven independent diarization evaluation (retrieved October 17, 2026)
Additional sourceLinagora Labs, LinTO speaker diarization benchmark (retrieved October 18, 2026)
Additional sourceArgmax OpenBench (retrieved October 18, 2026)
Additional sourceOmi Health Engineering, clinical batch diarization evaluation (retrieved October 21, 2026)
Additional sourceOcular Converse-Diarization Technical Report (retrieved October 21, 2026)
Additional sourceOmi Health clinical diarization benchmark (retrieved October 23, 2026)
Additional sourceModel metadata (retrieved October 17, 2026)12345
Additional sourceModel metadata (retrieved October 18, 2026)
Additional sourceOpenRouter: Popularity index (derived), CC BY 4.0
Additional sourceVercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional sourceOllama: cumulative downloads for the popularity index
Additional sourceReplicate: cumulative runs for the popularity index
Additional sourceGoogle Trending Now: limited feed selection for Germany and the US
Additional sourceCreative Commons Attribution 4.0