Voice Activity Detection
Transformers
PyTorch
TensorBoard
Safetensors
pyannet
speaker-diarization
speaker-segmentation
Generated from Trainer
pyannote
pyannote.audio
pyannote-audio-model
audio
voice
speech
speaker
speaker-change-detection
overlapped-speech-detection
resegmentation
Inference Endpoints
| model: | |
| _target_: pyannote.audio.models.segmentation.PyanNet.PyanNet | |
| linear: | |
| hidden_size: 128 | |
| num_layers: 2 | |
| lstm: | |
| batch_first: true | |
| bidirectional: true | |
| dropout: 0.0 | |
| hidden_size: 128 | |
| monolithic: true | |
| num_layers: 4 | |
| num_channels: 1 | |
| sample_rate: 16000 | |
| sincnet: | |
| sample_rate: 16000 | |
| stride: 10 | |
| task: | |
| duration: 10.0 | |
| max_speakers_per_chunk: 3 | |
| max_speakers_per_frame: 2 | |