pyannote-segmentation

4
license:mit
by
it-just-works
Audio Model
OTHER
New
4 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
Unknown
Mobile
Laptop
Server
Quick Summary

Using this open-source model in production?

Code Examples

waveform (first row)python
# waveform (first row)
duration, sample_rate, num_channels = 10, 16000, 1
waveform = torch.randn(batch_size, num_channels, duration * sample_rate) 

# powerset multi-class encoding (second row)
powerset_encoding = model(waveform)

# multi-label encoding (third row)
from pyannote.audio.utils.powerset import Powerset
max_speakers_per_chunk, max_speakers_per_frame = 3, 2
to_multilabel = Powerset(
    max_speakers_per_chunk, 
    max_speakers_per_frame).to_multilabel
multilabel_encoding = to_multilabel(powerset_encoding)
waveform (first row)python
# waveform (first row)
duration, sample_rate, num_channels = 10, 16000, 1
waveform = torch.randn(batch_size, num_channels, duration * sample_rate) 

# powerset multi-class encoding (second row)
powerset_encoding = model(waveform)

# multi-label encoding (third row)
from pyannote.audio.utils.powerset import Powerset
max_speakers_per_chunk, max_speakers_per_frame = 3, 2
to_multilabel = Powerset(
    max_speakers_per_chunk, 
    max_speakers_per_frame).to_multilabel
multilabel_encoding = to_multilabel(powerset_encoding)
waveform (first row)python
# waveform (first row)
duration, sample_rate, num_channels = 10, 16000, 1
waveform = torch.randn(batch_size, num_channels, duration * sample_rate) 

# powerset multi-class encoding (second row)
powerset_encoding = model(waveform)

# multi-label encoding (third row)
from pyannote.audio.utils.powerset import Powerset
max_speakers_per_chunk, max_speakers_per_frame = 3, 2
to_multilabel = Powerset(
    max_speakers_per_chunk, 
    max_speakers_per_frame).to_multilabel
multilabel_encoding = to_multilabel(powerset_encoding)
waveform (first row)python
# waveform (first row)
duration, sample_rate, num_channels = 10, 16000, 1
waveform = torch.randn(batch_size, num_channels, duration * sample_rate) 

# powerset multi-class encoding (second row)
powerset_encoding = model(waveform)

# multi-label encoding (third row)
from pyannote.audio.utils.powerset import Powerset
max_speakers_per_chunk, max_speakers_per_frame = 3, 2
to_multilabel = Powerset(
    max_speakers_per_chunk, 
    max_speakers_per_frame).to_multilabel
multilabel_encoding = to_multilabel(powerset_encoding)
waveform (first row)python
# waveform (first row)
duration, sample_rate, num_channels = 10, 16000, 1
waveform = torch.randn(batch_size, num_channels, duration * sample_rate) 

# powerset multi-class encoding (second row)
powerset_encoding = model(waveform)

# multi-label encoding (third row)
from pyannote.audio.utils.powerset import Powerset
max_speakers_per_chunk, max_speakers_per_frame = 3, 2
to_multilabel = Powerset(
    max_speakers_per_chunk, 
    max_speakers_per_frame).to_multilabel
multilabel_encoding = to_multilabel(powerset_encoding)
waveform (first row)python
# waveform (first row)
duration, sample_rate, num_channels = 10, 16000, 1
waveform = torch.randn(batch_size, num_channels, duration * sample_rate) 

# powerset multi-class encoding (second row)
powerset_encoding = model(waveform)

# multi-label encoding (third row)
from pyannote.audio.utils.powerset import Powerset
max_speakers_per_chunk, max_speakers_per_frame = 3, 2
to_multilabel = Powerset(
    max_speakers_per_chunk, 
    max_speakers_per_frame).to_multilabel
multilabel_encoding = to_multilabel(powerset_encoding)
waveform (first row)python
# waveform (first row)
duration, sample_rate, num_channels = 10, 16000, 1
waveform = torch.randn(batch_size, num_channels, duration * sample_rate) 

# powerset multi-class encoding (second row)
powerset_encoding = model(waveform)

# multi-label encoding (third row)
from pyannote.audio.utils.powerset import Powerset
max_speakers_per_chunk, max_speakers_per_frame = 3, 2
to_multilabel = Powerset(
    max_speakers_per_chunk, 
    max_speakers_per_frame).to_multilabel
multilabel_encoding = to_multilabel(powerset_encoding)
waveform (first row)python
# waveform (first row)
duration, sample_rate, num_channels = 10, 16000, 1
waveform = torch.randn(batch_size, num_channels, duration * sample_rate) 

# powerset multi-class encoding (second row)
powerset_encoding = model(waveform)

# multi-label encoding (third row)
from pyannote.audio.utils.powerset import Powerset
max_speakers_per_chunk, max_speakers_per_frame = 3, 2
to_multilabel = Powerset(
    max_speakers_per_chunk, 
    max_speakers_per_frame).to_multilabel
multilabel_encoding = to_multilabel(powerset_encoding)
waveform (first row)python
# waveform (first row)
duration, sample_rate, num_channels = 10, 16000, 1
waveform = torch.randn(batch_size, num_channels, duration * sample_rate) 

# powerset multi-class encoding (second row)
powerset_encoding = model(waveform)

# multi-label encoding (third row)
from pyannote.audio.utils.powerset import Powerset
max_speakers_per_chunk, max_speakers_per_frame = 3, 2
to_multilabel = Powerset(
    max_speakers_per_chunk, 
    max_speakers_per_frame).to_multilabel
multilabel_encoding = to_multilabel(powerset_encoding)
Usagepython
# instantiate the model
from pyannote.audio import Model
model = Model.from_pretrained(
  "pyannote/segmentation-3.0", 
  use_auth_token="HUGGINGFACE_ACCESS_TOKEN_GOES_HERE")
Usagepython
# instantiate the model
from pyannote.audio import Model
model = Model.from_pretrained(
  "pyannote/segmentation-3.0", 
  use_auth_token="HUGGINGFACE_ACCESS_TOKEN_GOES_HERE")
Usagepython
# instantiate the model
from pyannote.audio import Model
model = Model.from_pretrained(
  "pyannote/segmentation-3.0", 
  use_auth_token="HUGGINGFACE_ACCESS_TOKEN_GOES_HERE")
Usagepython
# instantiate the model
from pyannote.audio import Model
model = Model.from_pretrained(
  "pyannote/segmentation-3.0", 
  use_auth_token="HUGGINGFACE_ACCESS_TOKEN_GOES_HERE")
Usagepython
# instantiate the model
from pyannote.audio import Model
model = Model.from_pretrained(
  "pyannote/segmentation-3.0", 
  use_auth_token="HUGGINGFACE_ACCESS_TOKEN_GOES_HERE")
Usagepython
# instantiate the model
from pyannote.audio import Model
model = Model.from_pretrained(
  "pyannote/segmentation-3.0", 
  use_auth_token="HUGGINGFACE_ACCESS_TOKEN_GOES_HERE")
Usagepython
# instantiate the model
from pyannote.audio import Model
model = Model.from_pretrained(
  "pyannote/segmentation-3.0", 
  use_auth_token="HUGGINGFACE_ACCESS_TOKEN_GOES_HERE")
Usagepython
# instantiate the model
from pyannote.audio import Model
model = Model.from_pretrained(
  "pyannote/segmentation-3.0", 
  use_auth_token="HUGGINGFACE_ACCESS_TOKEN_GOES_HERE")
Usagepython
# instantiate the model
from pyannote.audio import Model
model = Model.from_pretrained(
  "pyannote/segmentation-3.0", 
  use_auth_token="HUGGINGFACE_ACCESS_TOKEN_GOES_HERE")
Voice activity detectionpython
from pyannote.audio.pipelines import VoiceActivityDetection
pipeline = VoiceActivityDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
vad = pipeline("audio.wav")
# `vad` is a pyannote.core.Annotation instance containing speech regions
Voice activity detectionpython
from pyannote.audio.pipelines import VoiceActivityDetection
pipeline = VoiceActivityDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
vad = pipeline("audio.wav")
# `vad` is a pyannote.core.Annotation instance containing speech regions
Voice activity detectionpython
from pyannote.audio.pipelines import VoiceActivityDetection
pipeline = VoiceActivityDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
vad = pipeline("audio.wav")
# `vad` is a pyannote.core.Annotation instance containing speech regions
Voice activity detectionpython
from pyannote.audio.pipelines import VoiceActivityDetection
pipeline = VoiceActivityDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
vad = pipeline("audio.wav")
# `vad` is a pyannote.core.Annotation instance containing speech regions
Voice activity detectionpython
from pyannote.audio.pipelines import VoiceActivityDetection
pipeline = VoiceActivityDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
vad = pipeline("audio.wav")
# `vad` is a pyannote.core.Annotation instance containing speech regions
Voice activity detectionpython
from pyannote.audio.pipelines import VoiceActivityDetection
pipeline = VoiceActivityDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
vad = pipeline("audio.wav")
# `vad` is a pyannote.core.Annotation instance containing speech regions
Voice activity detectionpython
from pyannote.audio.pipelines import VoiceActivityDetection
pipeline = VoiceActivityDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
vad = pipeline("audio.wav")
# `vad` is a pyannote.core.Annotation instance containing speech regions
Voice activity detectionpython
from pyannote.audio.pipelines import VoiceActivityDetection
pipeline = VoiceActivityDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
vad = pipeline("audio.wav")
# `vad` is a pyannote.core.Annotation instance containing speech regions
Voice activity detectionpython
from pyannote.audio.pipelines import VoiceActivityDetection
pipeline = VoiceActivityDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
vad = pipeline("audio.wav")
# `vad` is a pyannote.core.Annotation instance containing speech regions
`vad` is a pyannote.core.Annotation instance containing speech regionspython
from pyannote.audio.pipelines import OverlappedSpeechDetection
pipeline = OverlappedSpeechDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove overlapped speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-overlapped speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
osd = pipeline("audio.wav")
# `osd` is a pyannote.core.Annotation instance containing overlapped speech regions
`vad` is a pyannote.core.Annotation instance containing speech regionspython
from pyannote.audio.pipelines import OverlappedSpeechDetection
pipeline = OverlappedSpeechDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove overlapped speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-overlapped speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
osd = pipeline("audio.wav")
# `osd` is a pyannote.core.Annotation instance containing overlapped speech regions
`vad` is a pyannote.core.Annotation instance containing speech regionspython
from pyannote.audio.pipelines import OverlappedSpeechDetection
pipeline = OverlappedSpeechDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove overlapped speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-overlapped speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
osd = pipeline("audio.wav")
# `osd` is a pyannote.core.Annotation instance containing overlapped speech regions
`vad` is a pyannote.core.Annotation instance containing speech regionspython
from pyannote.audio.pipelines import OverlappedSpeechDetection
pipeline = OverlappedSpeechDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove overlapped speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-overlapped speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
osd = pipeline("audio.wav")
# `osd` is a pyannote.core.Annotation instance containing overlapped speech regions
`vad` is a pyannote.core.Annotation instance containing speech regionspython
from pyannote.audio.pipelines import OverlappedSpeechDetection
pipeline = OverlappedSpeechDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove overlapped speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-overlapped speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
osd = pipeline("audio.wav")
# `osd` is a pyannote.core.Annotation instance containing overlapped speech regions
`vad` is a pyannote.core.Annotation instance containing speech regionspython
from pyannote.audio.pipelines import OverlappedSpeechDetection
pipeline = OverlappedSpeechDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove overlapped speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-overlapped speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
osd = pipeline("audio.wav")
# `osd` is a pyannote.core.Annotation instance containing overlapped speech regions
`vad` is a pyannote.core.Annotation instance containing speech regionspython
from pyannote.audio.pipelines import OverlappedSpeechDetection
pipeline = OverlappedSpeechDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove overlapped speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-overlapped speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
osd = pipeline("audio.wav")
# `osd` is a pyannote.core.Annotation instance containing overlapped speech regions
`vad` is a pyannote.core.Annotation instance containing speech regionspython
from pyannote.audio.pipelines import OverlappedSpeechDetection
pipeline = OverlappedSpeechDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove overlapped speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-overlapped speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
osd = pipeline("audio.wav")
# `osd` is a pyannote.core.Annotation instance containing overlapped speech regions
`vad` is a pyannote.core.Annotation instance containing speech regionspython
from pyannote.audio.pipelines import OverlappedSpeechDetection
pipeline = OverlappedSpeechDetection(segmentation=model)
HYPER_PARAMETERS = {
  # remove overlapped speech regions shorter than that many seconds.
  "min_duration_on": 0.0,
  # fill non-overlapped speech regions shorter than that many seconds.
  "min_duration_off": 0.0
}
pipeline.instantiate(HYPER_PARAMETERS)
osd = pipeline("audio.wav")
# `osd` is a pyannote.core.Annotation instance containing overlapped speech regions

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.