OpenTranscribe

    Self-hosted AI-powered transcription platform with speaker diarization, search, and collaboration features. Built with Svelte, FastAPI, and Docker for easy deployment.

    Language: python

    Author: Rich Chambers (@rich_chambers)

    14 stars · 314 views

    Files

    • 2.2h_7998s__cap-8.0__bs-128__mp-on__r1.json (json)
    • 0.5h_1899s__cap-unl__bs-256__mp-on__r0.json (json)
    • 0.5h_1899s__cap-4.0__bs-32__mp-off__r0.json (json)
    • 2.2h_7998s__cap-unl__bs-192__mp-off__r0.json (json)
    • 0.5h_1899s__cap-unl__bs-128__mp-on__r1.json (json)
    • 0.5h_1899s__cap-unl__bs-128__mp-off__r0.json (json)
    • 0.5h_1899s__cap-4.0__bs-64__mp-off__r0.json (json)
    • 0.5h_1899s__cap-4.0__bs-32__mp-on__r0.json (json)
    • 2.2h_7998s__cap-8.0__bs-128__mp-on__r0.json (json)
    • 0.5h_1899s__cap-8.0__bs-192__mp-on__r1.json (json)
    • 0.5h_1899s__cap-8.0__bs-32__mp-off__r0.json (json)
    • 0.5h_1899s__cap-unl__bs-128__mp-off__r1.json (json)
    • 0.5h_1899s__cap-8.0__bs-192__mp-off__r1.json (json)
    • 0.5h_1899s__cap-unl__bs-64__mp-on__r0.json (json)
    • 0.5h_1899s__cap-4.0__bs-192__mp-off__r1.json (json)
    • 2.2h_7998s__cap-4.0__bs-64__mp-on__r0.json (json)
    • 2.2h_7998s__cap-unl__bs-256__mp-on__r0.json (json)
    • 0.5h_1899s__cap-8.0__bs-256__mp-off__r0.json (json)
    • 0.5h_1899s__cap-8.0__bs-32__mp-on__r0.json (json)
    • 2.2h_7998s__cap-4.0__bs-64__mp-on__r1.json (json)
    • 2.2h_7998s__cap-8.0__bs-64__mp-off__r1.json (json)
    • 2.2h_7998s__cap-unl__bs-128__mp-on__r1.json (json)
    • 0.5h_1899s__cap-unl__bs-64__mp-off__r1.json (json)
    • 0.5h_1899s__cap-8.0__bs-256__mp-on__r1.json (json)
    • 0.5h_1899s__cap-4.0__bs-16__mp-on__r0.json (json)
    • 2.2h_7998s__cap-8.0__bs-256__mp-on__r1.json (json)
    • 0.5h_1899s__cap-unl__bs-64__mp-on__r1.json (json)
    • 2.2h_7998s__cap-unl__bs-256__mp-off__r1.json (json)
    • 2.2h_7998s__cap-4.0__bs-128__mp-off__r1.json (json)
    • 0.5h_1899s__cap-4.0__bs-64__mp-on__r1.json (json)
    • 0.5h_1899s__cap-unl__bs-192__mp-on__r1.json (json)
    • 0.5h_1899s__cap-unl__bs-16__mp-on__r0.json (json)
    • 2.2h_7998s__cap-unl__bs-64__mp-on__r1.json (json)
    • 2.2h_7998s__cap-unl__bs-64__mp-off__r1.json (json)
    • 0.5h_1899s__cap-unl__bs-16__mp-off__r0.json (json)
    • mps (txt)
    • test_0.5h__mps__bs-16__mp-off__r0.json (json)
    • test_0.5h__mps__bs-1__mp-off__r0.json (json)
    • test_0.5h__mps__bs-64__mp-off__r0.json (json)
    • test_0.5h__mps__bs-8__mp-off__r0.json (json)
    • test_0.5h__mps__bs-4__mp-off__r0.json (json)
    • test_0.5h__mps__bs-32__mp-off__r0.json (json)
    • 0.5h_1899s__cap-unl__bs-192__mp-off__r1.json (json)
    • 2.2h_7998s__cap-unl__bs-192__mp-on__r1.json (json)
    • 0.5h_1899s__cap-4.0__bs-192__mp-off__r0.json (json)
    • 2.2h_7998s__cap-unl__bs-256__mp-on__r1.json (json)
    • 0.5h_1899s__cap-4.0__bs-128__mp-on__r0.json (json)
    • 2.2h_7998s__cap-8.0__bs-128__mp-off__r1.json (json)
    • 2.2h_7998s__cap-8.0__bs-64__mp-off__r0.json (json)
    • 0.5h_1899s__cap-4.0__bs-16__mp-off__r0.json (json)
    • 2.2h_7998s__cap-unl__bs-192__mp-off__r1.json (json)
    • 0.5h_1899s__cap-4.0__bs-64__mp-off__r1.json (json)
    • 2.2h_7998s__cap-unl__bs-64__mp-off__r0.json (json)
    • 0.5h_1899s__cap-unl__bs-256__mp-off__r1.json (json)
    • 0.5h_1899s__cap-8.0__bs-128__mp-off__r0.json (json)
    • 0.5h_1899s__cap-8.0__bs-16__mp-off__r0.json (json)
    • 2.2h_7998s__cap-4.0__bs-128__mp-on__r0.json (json)
    • 2.2h_7998s__cap-unl__bs-192__mp-on__r0.json (json)
    • 2.2h_7998s__cap-unl__bs-64__mp-on__r0.json (json)
    • 0.5h_1899s__cap-unl__bs-32__mp-on__r0.json (json)
    • 2.2h_7998s__cap-4.0__bs-192__mp-on__r1.json (json)
    • 0.5h_1899s__cap-8.0__bs-256__mp-on__r0.json (json)
    • 0.5h_1899s__cap-4.0__bs-128__mp-off__r1.json (json)
    • 0.5h_1899s__cap-8.0__bs-64__mp-on__r1.json (json)
    • 2.2h_7998s__cap-8.0__bs-64__mp-on__r0.json (json)
    • 2.2h_7998s__cap-4.0__bs-256__mp-off__r1.json (json)
    • 0.5h_1899s__cap-4.0__bs-256__mp-on__r1.json (json)
    • 2.2h_7998s__cap-4.0__bs-256__mp-on__r0.json (json)
    • 2.2h_7998s__cap-unl__bs-128__mp-on__r0.json (json)
    • 0.5h_1899s__cap-8.0__bs-192__mp-on__r0.json (json)
    • 2.2h_7998s__cap-8.0__bs-64__mp-on__r1.json (json)
    • 0.5h_1899s__cap-4.0__bs-64__mp-on__r0.json (json)
    • 2.2h_7998s__cap-unl__bs-128__mp-off__r0.json (json)
    • 0.5h_1899s__cap-unl__bs-32__mp-off__r0.json (json)
    • 2.2h_7998s__cap-4.0__bs-192__mp-on__r0.json (json)
    • 2.2h_7998s__cap-8.0__bs-256__mp-off__r0.json (json)
    • 2.2h_7998s__cap-4.0__bs-256__mp-on__r1.json (json)
    • 0.5h_1899s__cap-4.0__bs-128__mp-off__r0.json (json)
    • whole-stack (txt)
    • 0.5h_1899s__cap-8GB__whisper-base__bs-16.json (json)
    • 0.5h_1899s__cap-unl__whisper-base__bs-16.json (json)
    • 0.5h_1899s__cap-8GB__whisper-small__bs-16.json (json)
    • 0.5h_1899s__cap-4GB__whisper-medium__bs-16.json (json)
    • 0.5h_1899s__cap-4GB__whisper-base__bs-16.json (json)
    • 0.5h_1899s__cap-8GB__whisper-medium__bs-16.json (json)
    • 0.5h_1899s__cap-unl__whisper-small__bs-16.json (json)
    • 0.5h_1899s__cap-6GB__whisper-medium__bs-16.json (json)
    • 0.5h_1899s__cap-6GB__whisper-small__bs-16.json (json)
    • 0.5h_1899s__cap-unl__whisper-medium__bs-16.json (json)
    • 0.5h_1899s__cap-4GB__whisper-small__bs-16.json (json)
    • 0.5h_1899s__cap-6GB__whisper-base__bs-16.json (json)
    • 2.2h_7998s__cap-8.0__bs-192__mp-on__r0.json (json)
    • 2.2h_7998s__cap-4.0__bs-256__mp-off__r0.json (json)
    • 2.2h_7998s__cap-4.0__bs-128__mp-on__r1.json (json)
    • cpu (txt)
    • commit-push-pr.md (md)
    • __screenshots__ (txt)
    • fixtures (txt)
    • redaction (txt)
    • boundary (txt)
    • onnx (txt)
    • transcription (txt)
    • api (txt)
    • endpoints (txt)
    • .claude (claude)
    • commands (txt)
    • frontend (txt)
    • static (txt)
    • icons (txt)
    • scripts (txt)
    • plugins (txt)
    • src (txt)
    • lib (txt)
    • i18n (txt)
    • locales (txt)
    • utils (txt)
    • export (txt)
    • actions (txt)
    • workers (txt)
    • services (txt)
    • types (txt)
    • session (txt)
    • fileDetail (txt)
    • components (txt)
    • api (txt)
    • routes (txt)
    • forgot-password (txt)
    • search (txt)
    • reset-password (txt)
    • file-status (txt)
    • register (txt)
    • login (txt)
    • speakers (txt)
    • files (txt)
    • [id] (txt)
    • stores (txt)
    • ATTRIBUTION.md (markdown)
    • .windsurf (windsurf)
    • workflows (txt)
    • README.md (md)
    • phase-1-5-mps-fallback-hunt.md (md)
    • phase-5-2-implementation-results.md (md)
    • PR_DRAFT.md (md)
    • phase-6-2-lessons-learned.md (md)
    • versions (txt)
    • PROGRESS_REPORT.md (md)
    • phase-5-2-gpu-aggregate-and-reconstruct.md (md)
    • utils (txt)
    • transcription (txt)
    • phase-6-3-torch-compile-attempt.md (md)
    • db (txt)
    • core (txt)
    • middleware (txt)
    • scripts (txt)
    • transcription (txt)
    • phase-5-3-mps-optimization.md (md)
    • engine (txt)
    • phase-3-measurement.md (md)
    • phase-3-5-and-4-measurement.md (md)
    • phase-6-1-torch-compile-enablement.md (md)
    • backends (txt)
    • diarizers (txt)
    • phase-5-4-concurrent-requests-ceiling.md (md)
    • phase-6-3-shape-profile-attempt.md (md)
    • vram-budget-table.md (md)
    • phase-5-1-cuda-graphs.md (md)
    • phase-6-3-tensorrt-plan-build-on-startup.md (md)
    • docker-compose.prod.yml (yml)
    • docker-compose.watch.yml (yml)
    • docker-compose.benchmark.yml (yml)
    • database-schema.md (md)
    • YOUTUBE_COOKIE_AUTH.md (md)
    • LDAP_AUTH.md (md)
    • CROSS_PLATFORM_README.md (md)
    • YOUTUBE_ANTI_BOT_QUICKSTART.md (md)
    • diarization-boundary-results (txt)
    • __init__.py (py)
    • cloud-comparison.md (md)
    • dataset-sweep.md (md)
    • SEARCH_ARCHITECTURE.md (md)
    • PROMPT_ENGINEERING_GUIDE.md (md)
    • GPU_PIPELINE_OPTIMIZATION_PLAN.md (md)
    • REMOTE_BUILDER_QUICKSTART.md (md)
    • benchmark-results (txt)
    • FIPS_COMPLIANCE.md (md)
    • GPU_OPTIMIZATION_RESULTS.md (md)
    • SUPER_ADMIN_GUIDE.md (md)
    • integration (txt)
    • PYANNOTE_OPTIMIZATION_SUMMARY.md (md)
    • TRITON_INFERENCE_RESEARCH.md (md)
    • ASR_CLOUD_TESTING.md (md)
    • testing (txt)
    • media_url_test_videos.md (md)
    • NGINX_SETUP.md (md)
    • BUILD_PIPELINE.md (md)
    • e2e (txt)
    • UPLOAD_SPEED_BENCHMARK_RESULTS.md (md)
    • SECURITY_SCANNING.md (md)
    • DOCUMENTATION_STRATEGY.md (md)
    • TRANSCRIPTION_OPTIMIZATION.md (md)
    • VERIFICATION_CHECKLIST.md (md)
    • run.txt (txt)
    • BENCHMARK_RESULTS.md (md)
    • DOCUMENTATION_IMPLEMENTATION_SUMMARY.md (md)
    • CPU_MODE_TESTING.md (md)
    • README_OPTIMIZATION.md (md)
    • combined-engine-design.md (md)
    • PROMPT_IMPROVEMENTS_IMPLEMENTATION.md (md)
    • SQUARESPACE_DNS_QUICKSTART.md (md)
    • RELEASE_PROCESS.md (md)
    • MIGRATION_STRATEGY.md (md)
    • BACKEND_DOCUMENTATION.md (md)
    • OPENSEARCH_ML_COMMONS_GUIDE.md (md)
    • PIPELINE_TIMING.md (md)
    • VLLM_OPTIMIZATION.md (md)
    • OPTIMIZATION_ROADMAP.md (md)
    • AUTH_DEPLOYMENT_GUIDE.md (md)
    • INSTALLATION.md (md)
    • ONNX_PRECONVERSION.md (md)
    • diarization-vram-profile (txt)
    • README.md (md)
    • transcribers (txt)
    • 0.5h_1899s__cap-4.0__bs-256__mp-on__r0.json (json)
    • 2.2h_7998s__cap-8.0__bs-256__mp-off__r1.json (json)
    • 0.5h_1899s__cap-4.0__bs-192__mp-on__r1.json (json)
    • 2.2h_7998s__cap-4.0__bs-64__mp-off__r0.json (json)
    • accuracy.json (json)
    • raw (txt)
    • services (txt)
    • 2.2h_7998s__cap-4.0__bs-64__mp-off__r1.json (json)
    • FRONTEND_AUTH_IMPLEMENTATION_PLAN.md (md)
    • 2.2h_7998s__cap-4.0__bs-192__mp-off__r0.json (json)
    • 2.2h_7998s__cap-8.0__bs-256__mp-on__r0.json (json)
    • engine-benchmark-results (txt)
    • 2.2h_7998s__cap-8.0__bs-192__mp-off__r1.json (json)
    • redaction (txt)
    • detectors (txt)
    • 0.5h_1899s__cap-8.0__bs-16__mp-on__r0.json (json)
    • 0.5h_1899s__cap-8.0__bs-128__mp-on__r0.json (json)
    • 2.2h_7998s__cap-4.0__bs-128__mp-off__r0.json (json)
    • 0.5h_1899s__cap-8.0__bs-128__mp-on__r1.json (json)
    • data (txt)
    • issue-153-per-transcription-model-selection.md (md)
    • 2.2h_7998s__cap-unl__bs-128__mp-off__r1.json (json)
    • issue-152-disable-ai-summary.md (md)
    • 2.2h_7998s__cap-8.0__bs-192__mp-on__r1.json (json)
    • 0.5h_1899s__cap-unl__bs-64__mp-off__r0.json (json)
    • 0.5h_1899s__cap-unl__bs-192__mp-on__r0.json (json)
    • phase-6-2-onnx-export-feasibility.md (md)
    • README.md (md)
    • docker-compose.gpu.yml (yml)
    • docker-compose.gpu-scale.yml (yml)
    • docs (txt)
    • ARCHITECTURE.md (md)
    • deployment (txt)
    • AWS_PRODUCTION.md (md)
    • DEPLOYMENT_CHECKLIST.md (md)
    • RELEASE_PLAN_v0.4.0.md (md)
    • FIPS_140_3_COMPLIANCE.md (md)
    • market-research (txt)
    • LITERATURE_REVIEW.md (md)
    • SPEAKER_CLUSTERING_RESEARCH.md (md)
    • cloud-asr-market-research.md (md)
    • market-and-roadmap.md (md)
    • competitor-landscape.md (md)
    • strategic-positioning.md (md)
    • DOCKER_DEPLOYMENT.md (md)
    • SECURITY.md (md)
    • BLACKWELL_SETUP.md (md)
    • PROMPT_ENGINEERING_README.md (md)
    • DECEMBER_2025_INTEGRATION.md (md)
    • whisper-vram-profile (txt)
    • README.md (md)
    • upstream-patches (txt)
    • phase-1-session-status.md (md)
    • phase-6-3-spike-results.md (md)
    • vectorization-audit.md (md)
    • final-gate-results.md (md)
    • 0.5h_1899s__dur-30s__torch-only__threads-8.json (json)
    • 0.5h_1899s__dur-30s__onnx-seg-fp32__threads-8.json (json)
    • 0.5h_1899s__dur-30s__onnx-seg-int8__threads-8.json (json)
    • 0.5h_1899s__cap-4.0__bs-256__mp-off__r0.json (json)
    • 0.5h_1899s__cap-8.0__bs-64__mp-off__r1.json (json)
    • 0.5h_1899s__cap-4.0__bs-128__mp-on__r1.json (json)
    • 2.2h_7998s__cap-8.0__bs-128__mp-off__r0.json (json)
    • 0.5h_1899s__cap-8.0__bs-128__mp-off__r1.json (json)
    • 0.5h_1899s__cap-8.0__bs-192__mp-off__r0.json (json)
    • 0.5h_1899s__cap-unl__bs-192__mp-off__r0.json (json)
    • rttm (txt)
    • 0.5h_1899s__cap-4.0__bs-256__mp-off__r1.json (json)
    • 2.2h_7998s__cap-8.0__bs-192__mp-off__r0.json (json)
    • 0.5h_1899s__cap-8.0__bs-256__mp-off__r1.json (json)
    • 0.5h_1899s__cap-unl__bs-128__mp-on__r0.json (json)
    • 2.2h_7998s__cap-unl__bs-256__mp-off__r0.json (json)
    • 0.5h_1899s__cap-unl__bs-256__mp-on__r1.json (json)
    • 0.5h_1899s__cap-4.0__bs-192__mp-on__r0.json (json)
    • 0.5h_1899s__cap-8.0__bs-64__mp-on__r0.json (json)
    • 0.5h_1899s__cap-unl__bs-256__mp-off__r0.json (json)
    • 2.2h_7998s__cap-4.0__bs-192__mp-off__r1.json (json)
    • 0.5h_1899s__cap-8.0__bs-64__mp-off__r0.json (json)
    • accuracy.md (md)
    • cpu-feasibility-plan.md (md)
    • whole-stack.md (md)
    • GPU_OPTIMIZATION_PATCHES.md (md)
    • BENCHMARK_GUIDE.md (md)
    • KEYCLOAK_SETUP.md (md)
    • LOCAL_LLM_FIREWALL.md (md)
    • README-OFFLINE.md (md)
    • README.md (md)
    • corpus_full.json (json)
    • summary.md (md)
    • IMPLEMENTATION_AUDIT_REPORT.md (md)
    • DEV_BACKEND_REDEPLOY.md (md)
    • CACHE_INVALIDATION.md (md)
    • GPU_PROFILING.md (md)
    • CONTRIBUTING.md (md)
    • TESTING_CHECKLIST.md (md)
    • FORK_IMPLEMENTATION_PLAN.md (md)
    • SPEAKER_PROFILE_FIX_PLAN.md (md)
    • ENV_VARIABLES_FIPS_140_3.md (md)
    • E2E_TEST_EXPANSION_PLAN.md (md)
    • CODE_OF_CONDUCT.md (md)
    • FORK_COMPARISON_vfilon.md (md)
    • PKI_SETUP.md (md)
    • benchmark-corpus (txt)
    • corpus.json (json)
    • WHISPER_TIMESTAMP_DRIFT_RESEARCH.md (md)
    • CUSTOM_DOMAIN_SETUP.md (md)
    • plans (txt)
    • issue-151-disable-diarization.md (md)
    • docker-compose.pki-dev.yml (yml)
    • docker-compose.smb-test.yml (yml)
    • docker-compose.gpu-split.yml (yml)
    • setup-opentranscribe.sh (sh)
    • .hadolint.yaml (yaml)
    • backend (txt)
    • requirements-lite.txt (txt)
    • requirements-dev.txt (txt)
    • README.md (md)
    • pyproject.toml (toml)
    • requirements-ci.txt (txt)
    • alembic (txt)
    • v250_add_speaker_clustering_indexes.py (py)
    • v352_add_requested_whisper_model.py (py)
    • v340_add_user_media_sources.py (py)
    • v367_add_cloud_seams.py (py)
    • v031_add_keycloak_pki_auth.py (py)
    • v100_optimize_query_performance.py (py)
    • protected_media_plugins (txt)
    • watch_sources (txt)
    • v140_add_word_timestamps.py (py)
    • v091_add_speaker_suggestion_source.py (py)
    • v310_add_speaker_constraints.py (py)
    • v270_add_profile_avatar.py (py)
    • v355_add_diarization_settings.py (py)
    • v290_add_password_reset_tokens.py (py)
    • search (txt)
    • asr (txt)
    • diarization (txt)
    • v330_add_shared_configs_and_prompts.py (py)
    • v030_add_ldap_auth.py (py)
    • v363_add_asr_access_key_id.py (py)
    • v230_add_auto_labeling.py (py)
    • v280_add_upload_sessions.py (py)
    • v071_add_transcript_segment_unique_constraint.py (py)
    • api (txt)
    • endpoints (txt)
    • files (txt)
    • scripts (txt)
    • tests (txt)
    • redaction (txt)
    • unit (txt)
    • v369_superuser_role_invariant.py (py)
    • v150_add_file_retention_settings.py (py)
    • v366_add_watch_sources.py (py)
    • v350_add_diarization_disabled.py (py)
    • v190_add_collection_default_prompt.py (py)
    • v211_add_sharing_constraints_and_indexes.py (py)
    • v320_add_cluster_suggested_name.py (py)
    • v072_add_queued_downloading_statuses.py (py)
    • v300_add_gender_confirmed.py (py)
    • v120_add_remaining_fk_indexes.py (py)
    • v090_add_error_category.py (py)
    • v360_add_file_pipeline_timing.py (py)
    • v365_add_prompt_shared_by.py (py)
    • user_settings_helpers.py (py)
    • schemas (txt)
    • auth (txt)
    • tasks (txt)
    • v070_pki_security.py (py)
    • v361_add_media_file_imohash.py (py)
    • v364_add_content_redaction.py (py)
    • v170_add_keycloak_refresh_token.py (py)
    • v060_add_transcript_overlap.py (py)
    • v160_add_allow_local_fallback.py (py)
    • v353_fix_segment_unique_index.py (py)
    • v260_add_cluster_quality_metrics.py (py)
    • v110_add_missing_fk_indexes.py (py)
    • v073_convert_filestatus_enum_to_varchar.py (py)
    • app (txt)
    • models (txt)

    Loading code snippet…