Automatic Speech Recognition
WhisperKit
Core ML
speakerkit
pyannote
diarization
speaker-diarization
whisper
asr
quantized
Instructions to use argmaxinc/speakerkit-pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- WhisperKit
How to use argmaxinc/speakerkit-pro with WhisperKit:
# Install CLI with Homebrew on macOS device brew install whisperkit-cli # View all available inference options whisperkit-cli transcribe --help # Download and run inference using whisper base model whisperkit-cli transcribe --audio-path /path/to/audio.mp3 # Or use your preferred model variant whisperkit-cli transcribe --model "large-v3" --model-prefix "distil" --audio-path /path/to/audio.mp3 --verbose
- Notebooks
- Google Colab
- Kaggle
metadata
license: other
license_name: argmax-fmod-license
license_link: https://huggingface.co/argmaxinc/speakerkit-pro/blob/main/LICENSE_NOTICE.txt
pretty_name: SpeakerKit
viewer: false
library_name: whisperkit
tags:
- speakerkit
- pyannote
- diarization
- speaker-diarization
- whisper
- whisperkit
- coreml
- asr
- quantized
- automatic-speech-recognition
extra_gated_heading: Request Access to SpeakerKit Pro (Part of Argmax SDK)
extra_gated_description: >-
SpeakerKit Pro is Argmax's state-of-the-art on-device framework for speaker
recognition tasks such as speaker diarization. Please submit your information
below or directly send an email to
[speakerkitpro@argmaxinc.com](mailto:speakerkitpro@argmaxinc.com).
extra_gated_fields:
Company: text
Work email: text
I acknowledge the license notice: checkbox
extra_gated_button_content: Submit
SpeakerKit Pro
Read the blog
Try it on TestFlight
Read the Research Paper to learn more about the architecture and performance benchmarks
Get access here