Pyannote
Rank:Average Model Cost: $0.0000
Number of Runs: 2,576,549
Models by this creator
segmentation
segmentation
The model is a speaker segmentation system that can be used for voice activity detection, overlapped speech detection, and resegmentation. It relies on the pyannote.audio package and provides raw scores as output. The model can be reproduced using the provided hyperparameters and has been evaluated with expected outputs and a VBx baseline.
$-/run
1.3M
Huggingface
speaker-diarization
speaker-diarization
The speaker-diarization model is a machine learning model that can recognize and separate different speakers in an audio recording. It uses various techniques such as clustering and classification algorithms to identify distinct speakers based on their unique characteristics, such as voice pitch, duration, and speaking style. This model is useful for a variety of applications, including transcription services, audio content analysis, and speech recognition systems.
$-/run
949.6K
Huggingface
embedding
embedding
The embedding model is designed to convert input text into a continuous representation in a high-dimensional vector space. This continuous representation, known as word embeddings or sentence embeddings, captures the semantic meaning and contextual information of the input text. The model uses neural networks to learn the embeddings based on a large amount of training data. These embeddings can be used for various natural language processing tasks, such as text classification, sentiment analysis, and information retrieval.
$-/run
129.1K
Huggingface
voice-activity-detection
voice-activity-detection
The voice-activity-detection model is a module in the pyannote.audio library that allows for the detection of speech activity in audio signals. It relies on the pyannote.audio 2.1 library and can be used for various applications such as speaker diarization and automatic speech recognition. The model can be installed by following the provided instructions and support can be obtained from the creator through commercial or technical channels.
$-/run
124.9K
Huggingface
speaker-segmentation
speaker-segmentation
The speaker-segmentation model is a model that is capable of identifying and separating individual speakers in an audio recording. This model uses advanced techniques like speech recognition and audio processing to accurately analyze the audio and detect different speaker segments. By using this model, it is possible to automatically transcribe and identify speakers in a multi-speaker audio recording, which can be extremely useful for applications like transcription services, voice assistants, and audio analysis.
$-/run
16.1K
Huggingface
overlapped-speech-detection
overlapped-speech-detection
The overlapped-speech-detection model is designed to identify and detect periods of overlapped speech in audio recordings. It is trained to separate and distinguish the speech of multiple speakers who are talking simultaneously, making it useful for applications such as transcription or speaker diarization.
$-/run
15.5K
Huggingface
TestModelForContinuousIntegration
TestModelForContinuousIntegration
Dummy model used for continuous integration purposes
$-/run
523
Huggingface
brouhaha
brouhaha
šļøš„šØš Brouhaha Joint voice activity detection, speech-to-noise ratio, and C50 room acoustics estimation TL;DR | Paper | Code | And Now for Something Completely Different Installation This model relies on pyannote.audio and brouhaha-vad. Usage Citation
$-/run
212
Huggingface