Library/whisperX
Library/whisperXForked

m-bain/whisperX

whisperX

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

Builder

m-bain

m-bain

m-bain • individual

Stars

20,975

Using upstream star count

Forks

2,208

Using upstream fork count

Open Issues

0

Activity Score

0/100

0 commits in 30d

Created

Dec 9, 2022

Project creation date

README Summary

WhisperX is an enhanced version of OpenAI's Whisper that provides automatic speech recognition with precise word-level timestamps and speaker diarization capabilities. It improves upon the original Whisper by adding forced phoneme alignment to generate accurate word-level segmentation and integrates speaker identification to distinguish between different speakers in audio recordings.

AI Dev Skills

Unmapped

Automatic Speech RecognitionSpeaker DiarizationVoice Activity DetectionForced AlignmentAudio Signal ProcessingTransformer Fine-tuningMulti-model Pipeline IntegrationAudio Feature Extraction

Tags

Automatic Speech RecognitionSpeaker DiarizationVoice Activity DetectionForced AlignmentAudio Signal ProcessingTransformer Fine-tuningMulti-model Pipeline IntegrationAudio Feature ExtractionAccessibility CaptioningTime Series AlignmentCloud InfrastructureMulti-speaker RecognitionFoundation Model EnhancementAccessibility TechnologyMedia & EntertainmentTransformer ArchitectureMeeting Transcription with Speaker LabelsBroadcastingNeural Audio ProcessingCourt Recording TranscriptionAudio AILegal TechPodcast TranscriptionInterview AnalysisVideo SubtitlingHealthcareMultimodal AIAudioSelf-hostedMulti-speaker Audio AnalysisOn-premiseEducationPython

Taxonomy

Recent Activity

Updated 27 days ago

7 Days

0

30 Days

0

90 Days

0

Quality

beta
Quality
high
Maturity
beta

Categories

Model TrainingPrimaryEvals & BenchmarkingCoding & Dev ToolsHealthcare & BiologyFinance & LegalMultimodal AIOther AI / MLFoundation ModelsML Platform & InfrastructureSafety & AlignmentGenerative Media

PM Skills

Developer Platform

Languages

Python100.0%

Timeline

Project created
Dec 9, 2022
Forked
Mar 22, 2026
Your last push
27 days ago
Upstream last push
9 days ago
Tracked since
Mar 17, 2026

Similar Repos

pgvector cosine similarity · $0

Loading…