Model Details
Full Model IDpyannote/speaker-diarization-3.1
Pipeline / Taskautomatic-speech-recognition
Librarypyannote-audio
Downloads (all-time)10.2M
Likes1.8K
Last Modified5/10/2024
Author / Orgpyannote
PrivateNo — public
⚡ Quick Usage (Python)
Using the 🤗 Transformers library. Install with pip install transformers
from transformers import pipeline
# Load the model
pipe = pipeline("automatic-speech-recognition", model="pyannote/speaker-diarization-3.1")
# Run inference
result = pipe("Your input here")
print(result)🏷️ Tags
pyannote-audiopyannotepyannote-audio-pipelineaudiovoicespeechspeakerspeaker-diarizationspeaker-change-detectionvoice-activity-detectionoverlapped-speech-detectionautomatic-speech-recognitionarxiv:2111.14448arxiv:2012.01477license:mitendpoints_compatibleregion:us
More Speech Recognition Models
See all →🚀 Use This Model
Access model files, inference API, and full documentation on Hugging Face.
Open on Hugging Face →Browse Model Files ↗← Browse All Models🎙️ Task: Speech Recognition
This model is designed for the Speech Recognition task. Explore more models for this use case.
All Speech Recognition Models →📊 Popularity
⬇ Downloads10.2M
❤️ Community Likes1.8K
🛠️ Requirements
- →Install: pip install pyannote-audio
- →Python 3.8+ recommended for Transformers.
- →GPU (CUDA) speeds up inference significantly.
- →Use model.half() for fp16 on limited VRAM.