Model · Voice activity detection
Pyannote
Using this open-source model in production? Consider switching to pyannoteAI for better and faster options. This model ingests 10 seconds of mono audio sampled at 16kHz and outputs speaker diarization as a (numframes, numclasses) matrix where the 7 classes are non-speech, speaker #1, speaker #2, speaker #3, speakers #1 and #2, speakers #1 and #3, and speakers #2 and #3. The various concepts behind this model are described in details in this paper. It has been trained by Séverin Baroudi with pyannote.audio 3.0.0 using the combination of the training sets of AISHELL, AliMeeting, AMI, AVA-AVD, DIHARD, Ego4D, MSDWild, REPERE, and VoxConverse. This companion repository by Alexis Plaquet also…
Access requested at publisher
mit
pyannote-audio
Model · Voice activity detection
Pyannote
Using this open-source model in production? Consider switching to pyannoteAI for better and faster options. In order to reproduce the results of the paper "End-to-end speaker segmentation for overlap-aware resegmentation ", use pyannote/segmentation@Interspeech2021 with the following hyper-parameters: Expected outputs (and VBx baseline) are also provided in the /reproducibleresearch sub-directories.
Access requested at publisher
mit
pyannote-audio
Model · Voice activity detection
NVIDIA
For the detailed information, see the Overview subcard.
Access requested at publisher
other
nemo
Core AI (.aimodel) conversion of NVIDIA's streaming speaker-diarization model (up to eight speakers, 10 ms output frames) for iOS 27+ / macOS 27+. Converted from checkpoint revision (Nemotron-3-Diarization.nemo, SHA-256 867c53f552998f772e5b5e5c082962ae85ee7ca5669c2bc17d7f615133d4e96d) with coreai-torch 0.4.1 (standard graphs) and 0.4.2 (Neural Engine encoder), coreai-core 1.0.0b2. No weights were retrained, quantized or pruned. The model is split into two graphs that a host streaming loop calls once per encoder/head (packed speaker cache + FIFO + chunk embeddings → speaker probabilities). The Arrival-Order Speaker Cache, FIFO and chunking logic of Streaming Sortformer run on the host; see…
Open weights
openmdw-1.1
Core ML conversion of NVIDIA's streaming speaker-diarization model (up to eight speakers, 10 ms output frames) for iOS 18+ / macOS 15+. Converted from checkpoint revision (Nemotron-3-Diarization.nemo, SHA-256 No weights were retrained, quantized or pruned. The model is split into two graphs that a host streaming loop calls once per encoder/head (packed speaker cache + FIFO + chunk embeddings → speaker probabilities). The Arrival-Order Speaker Cache, FIFO and chunking logic of Streaming Sortformer run on the host and are not part of these graphs; see "Streaming loop" below..f32le files are raw little-endian float32 in C order. The.mlpackage directories load with MLModel.compileModel(at:) /…
Open weights
openmdw-1.1
coreml
GGUF conversions of NVIDIA's Nemotron-3 Diarization (Streaming Sortformer v3) for transcribe.cpp, the runtime behind speaker labels in Glimpse. The model answers "who spoke when" for up to 8 speakers at 10 ms resolution. It produces no text. AMI meeting corpus, IHM test set: 16 meetings, 9.06 hours. Scored against NVIDIA's forced-alignment RTTMs with a 0 s collar, overlapped speech included, and a plain 0.5 threshold at 10 ms with no post-processing. Every row went through the same pipeline. Compared with Sortformer v2.1, errors drop by 42% and speaker confusion by 76%, and the 1-second streaming mode beats v2.1's offline mode. Throughput on an Apple M2 Pro (offline mode, times faster than…
Open weights
other
