Spaces:

djhui5710
/

reachy_mini_home_assistant

Running

App Files Files Community

fix: set python version to work with default env

#3

by Domotick - opened Jan 16

base: refs/heads/main

←

from: refs/pr/3

Discussion Files changed

initial commit96083ea8

Initial commit: Reachy Mini Home Assistant Voice Assistantb7468817

Add Hugging Face Spaces metadata to README47cb5cba

Restructure app for Reachy Mini App Assistant4efaf4f9

Update repository URLs to Hugging Face552894a1

Fix README metadata: add sdk_version and app_filec017fe61

Add wake word models and sound filesd3686b7d

Fix pyproject.toml to match Reachy Mini app requirements12aed5f6

Update ESPHome protocol implementation to match official linux-voice-assistantf6b74401

Add back zeroconf/mDNS support for Home Assistant auto-discoveryd834e327

Fix import error: remove non-existent ListEntitiesServicesArgumentsResponsea7510f3a

Fix import error: use ListEntitiesMediaPlayerResponse (singular)58fd2a55

Remove __main__.py to avoid conflict with Reachy Mini app framework6a3e3dce

Add simple __main__.py for Hugging Face Spaces displayd00fdcaf

Make Hugging Face Spaces a static display page onlye8f8f407

Reorganize file structure for Reachy Mini app64faf24e

Fix app.py to properly run and handle stop eventf6e443c6

Add settings API endpoint for custom_app_url support19b23842

Rewrite app.py to use Reachy Mini's media APIbeec3f9d

Add scipy and soundfile dependencies for audio processingb3ae818f

Change custom_app_url to port 7860 for Reachy Mini settingsd77ff8d0

Add extensive logging and error handlingcea3a9b7

Simplify app.py to match official documentation665fc273

Rewrite app.py to match official template pattern055a9288

Refactor app.py to match official conversation app pattern5f199de8

Add scipy and soundfile dependencies4312d5fe

Add dont_start_webserver and use _get_instance_path()77a3517f

Remove scipy and soundfile dependencies8d4f1ef5

Restore scipy and soundfile dependenciesfaec4a47

Fix models.py to match original linux-voice-assistant5a4f598a

Add error handling for sound playback2a59be95

Restructure project to use src directory layout77d6a170

Fix static file paths and package-data5a3ccc3d

Fix paths for wakewords and sounds directoriesac2fd425

Match official conversation app configurationab7ff67c

Clean up project files and update README878ce1b6

Add comprehensive error handling and logging380eed8a

Remove daemon flag from threads to prevent premature termination273c16f1

Add parse_args() to match official conversation app structuree051e3d3

Test: Replace with official conversation app code8e27dfb9

Replace with official conversation appbdb449d1

Clean up temporary directories5820b446

Restore original project structure67699440

Add README.md with Hugging Face configuration6a3fb466

Create Hello World app for Reachy Mini7561bb30

feat: initial implementation of Reachy Mini Home Assistant Voice Assistant56430b3d

docs: update architecture to reflect Home Assistant STT/TTS6f4787d8

docs: update project plan to reflect Home Assistant STT/TTS architectureec3c0a45

docs: add Hugging Face Spaces README with configuration205bd666

docs: update requirements to reflect Home Assistant STT/TTS19d03c10

docs: add English versions of all documentation and clarify deployment090f72c0

docs: add wake word models and sounds documentationd149a39c

docs: add quick start guides for easy setup90389e2b

feat: add actual wake word models and sound effects9f1eacaf

feat: add scripts to download wake word models and sound effectsb3f0ffce

docs: update installation instructions to include model downloadfcdfcdf7

docs: update Chinese README to include model download instructionscb0faf13

feat: add automated installation scripts and model checkingb78364ce

docs: update README to emphasize automated installation23c71b80

feat: add one-click installation web UIb9b42259

docs: update README to highlight one-click web UI installation7ffaa4a8

feat: adapt application for Reachy Mini Application Storeaebd53df

chore: force refresh Hugging Face Space0ba80fff

refactor: remove local STT/TTS code (handled by Home Assistant)801f3a9e

fix: remove unused STT/TTS imports from main.pyae5f4438

refactor: remove all local STT/TTS dependencies and code2efbff78

"update"b8cfa607

"fix-dependencies"6b00c9d9

"cleanup-old-modules"bc98bd50

"fix-entry-point"36090e78

"restructure-for-app-store"7f421c98

"refactor-use-reachy-mini-native-audio"1562b352

"fix-huggingface-metadata"5525595c

"fix-zenoh-connection-error-fallback"b0aeccc8

"fix-graceful-fallback-when-zenoh-unavailable"f35a5cc0

"fix-zenoh-fallback-improved"f0dc6f27

"fix-runpy-warning-remove-main-import"419ece83

"fix-download-urls-use-linux-voice-assistant"f2dff397

"fix-huggingface-sdk-add-placeholder-app"dee13d20

"fix-gradio-version"aa125314

"fix-wakeword-json-format-for-pymicro-wakeword"218107bc

"fix-installation-instructions"5109765c

"fix-audio-processing-and-stable-device-id"9a11a2a2

"fix-audio-dtype-handling-for-bytes-and-string-types"d20112cf

"fix-convert-to-float32-before-mean-operations"68ddd2c5

"fix-simplify-audio-processing-based-on-official-sdk"0361f872

"fix-add-dtype-check-before-numeric-operations"db634b52

"fix-audio-processing-and-update-project-plan"e62bb6a0

Upload okay_nabu.tflite20395a69

Upload 31 files92eac807

Merge branch 'main' of https://huggingface.co/spaces/djhui5710/reachy_mini_ha_voice29fd1be3

"feat(entities):add-17-ESPHome-entities-for-full-robot-control"52380741

"feat(entities):complete-Phase-4-7-implementation"678efdc2

"docs:update-PROJECT_PLAN-file-list"b8736b0f

"docs:update-entity-tables-to-reflect-completed-status"ae768b80

fix bug641220d2

update PROJECT_PLAN.md4519d309

update folder84b1511f

change files5211f9d6

update gitignore0d53d1ed

"fix-reachy-controller-sdk-api-calls"e785f5d0

更新文档9d49e34f

"refactor-use-bundled-files-instead-of-download"701f0f56

"refactor-move-wakewords-and-sounds-into-package"40dea616

"fix-update-gitattributes-for-new-lfs-paths"9a32f45e

"fix-numpy-ufunc-type-mismatch-error"45876b9a

"fix-add-bundled-wakewords-and-sounds-files"7b42f6d6

"fix-pass-bytes-to-process_streaming-not-numpy-array"97902213

"fix-improve-audio-dtype-validation-and-error-handling"beedd8b1

"fix-rewrite-wake-word-processing-inline-like-reference"0b1f24f7

"fix-add-missing-command-handlers-and-fix-sensors-motion-api"74856bea

"fix-speaker-volume-control-via-daemon-api"f0af1cc4

"feat-add-doa-head-turning-on-wakeup"cdc9926c

"fix-remove-speech-detected-check-for-doa"d5437cfd

"fix-volume-api-path-add-api-prefix"1409d3e6

"feat-camera-add-mjpeg-streaming-server-for-home-assistant"c99f5033

"feat-add-emotion-buttons-and-microphone-volume-control"1e8f606c

"feat-add-camera-led-audio-entities"ec4e118a

"feat-replace-camera-status-with-camera-entity"6fd277fa

"feat-add-entity-category-for-config-entities"8abecb5d

"refactor-replace-emotion-buttons-with-select-dropdown"c775f956

"fix-microphone-volume-control-use-respeaker-helper"f2e56b31

"refactor-camera-to-url-remove-led-add-diagnostic-category"bbebe3c5

"fix-camera-url-use-wlan-ip-instead-of-placeholder"c3855eed

"feat-camera-use-esphome-camera-entity-for-real-preview"3825baeb

"fix-camera-add-CameraImageRequest-to-message-handler"424cea24

"fix-add-debug-logging-for-respeaker-availability"f2ca245d

"fix-CameraImageRequest-has-no-key-field"dadb1e9e

"fix-duplicate-entity-registration-and-camera-integration"80662a90

Update app9da872f3

Update app4c3306f9

Update app944b84ff

更新内容60be3dea

Merge branch 'main' of https://huggingface.co/spaces/djhui5710/reachy_mini_ha_voice287bae9c

Merge branch 'main' of https://huggingface.co/spaces/djhui5710/reachy_mini_ha_voice3f4996cc

更新readme7835cded

update readmeb77befa2

fix_duplicate_code_and_update_docsada03c02

"refactor:simplify-controls"e298bb38

✨ feat(esphome): add head joints JSON sensor for 3D visualization12f9fe4d

update passive data8d11d085

更新IPa3e5c524

\"fix: update SDK to docker for proper Reachy Mini Python App tag\"560807df

\"fix: restore Gradio SDK config\"848f3f28

\"fix: change SDK to static for proper Reachy Mini App display\"c730107b

\"chore: remove app.py\"6805cf02

\"docs: simplify README\"5a46d4cb

\"feat: update index.html with app content\"fd06a121

\"fix: correct app description\"699bb010

\"style: adopt Home Assistant color scheme\"fdc08ee2

\"fix: smooth color transitions\"584fdf10

\"fix: remove gap between hero and content\"adcffe97

\"refactor: merge duplicate sections\"4dbe61e2

\"style: adopt HA Material Design\"eec05e84

\"fix: revert CSS to working version\"b8b20325

feat(ha): add Reachy Mini 3D visualization card523e4255

chore(ha): remove unnecessary files8fffada0

去除不需要的文件44677224

优化拆分代码07e9e3ce

\"chore(release): version 0.1.5\"4e5c3ed2

优化程序崩溃58f00d3d

fix the motion377d38f3

removed wrong workflow6d6af93e

优化代码89da2bd5

update framework6563dc68

"fix_connection_error_handling"bf2418d0

"fix_shutdown_handling"31155323

"refactor_sdk_compliance"93089026

"fix_event_loop_blocking"524d696b

release version 0.2.02249ce8f

feat: add automatic facial expressions during conversation87fd0427

fix: make emotion playback non-blocking to prevent voice control issues137eac29

refactor: integrate emotion playback into MovementManager queue system24eb1f81

refactor: optimize conversation motion feedback system5322fcdc

docs: update PROJECT_PLAN and optimize motion feedbackf526ff16

"revert_to_version_0.2.0"634577b7

v0.2.1: Fix daemon crash issue and optimize codef3abae31

v0.2.2: Fix second conversation motion failure - Reduce control loop from 20Hz to 10Hz - Improve connection recovery (faster reconnect, 2s interval) - Add consecutive error tracking before marking connection lost - More robust error handling for transient connection issues99494170

v0.2.3: Fix daemon crash caused by conflicting pose commands - Disable pose setter methods in ReachyController (head_x/y/z, head_roll/pitch/yaw, body_yaw, antenna_left/right, look_at) - These setters conflict with MovementManager's 10Hz control loop - Per PROJECT_PLAN.md principle 7: voice conversation is highest priority - Pose control is now exclusively handled by MovementManager - Update version in __init__.pybe4ed943

v0.2.4: Fix microphone volume control - Use daemon HTTP API (/api/volume/microphone/set) instead of ReSpeaker DSP parameters - This matches the official implementation using amixer commands5f89e0de

Update installation steps: add 'Show community apps' checkbox stepb30312aa

更新tag581d1e5a

update readmecfd357d4

v0.2.6: Add thread-safe ReSpeaker USB access to prevent daemon deadlockedbcbf8f

Fix: Check satellite initialization before accessing _is_streaming_audioe2a702af

Fix: Move _is_streaming_audio init to early in __init__ before entity setupb713cdaa

Fix: Move _ReSpeakerContext class to correct position (before ReachyController)312c52fa

v0.2.7: Add DOA caching to prevent ReSpeaker query overload0c6d1293

v0.2.8: Replace DOA with YOLO face trackingbeb8e322

docs: Update PROJECT_PLAN.md - add face tracking, update Phase 14/17a26fdbd0

fix: Fix pyproject.toml TOML syntax error68fc9006

v0.2.9: Remove DOA/speech detection - replaced by face tracking7c7622b3

fix: Use push_audio_sample instead of play_sound to avoid GStreamer conflictsd63dd5f8

debug: Add logging for motion and audio initializationbf7c9010

fix: Use gstreamer media_backend + add debug logging for motion init2c4f920f

v0.2.10: Add debug logging for motion init + fix audio fallback samplerate9ef4811c

v0.2.11: Disable wakeup sound to prevent daemon crash + add debug loggingfe0a85bc

fix: Remove redundant import timeb0d765d0

fix: Remove unnecessary import and sleep1c9ecdc5

v0.2.12: Disable breathing animation to prevent serial port overflow7156a719

v0.2.13: Don't manually start/stop media - let SDK/daemon manage iteefe86cf

v0.2.14: Pause audio recording during TTS playback to prevent GStreamer conflicts529d5dbb

v0.2.15: Use play_sound() instead of push_audio_sample() for TTSd94735f3

v0.2.16: Fix TTS playback - pause recording during playbackcd59e9ef

v0.2.17: Remove head_joints/passive_joints, move error_message to diagnostica88f8844

v0.2.18: Fix audio playback - restore wakeup sound, use push_audio_sample0832ea31

v0.2.19: Force localhost connection mode to prevent WebRTC errorsae47b888

v0.2.20: Revert audio/satellite/voice_assistant/models/main to v0.2.9 working state29b7fc29

v0.2.21: Fix daemon crash - reduce control loop to 2Hz, pause during audio7edbf675

Revert "v0.2.21: Fix daemon crash - reduce control loop to 2Hz, pause during audio"6a4df6d0

feat: 优化人脸追踪和修复Music Assistant兼容性770da68f

feat: add tap sensitivity slider entity for Home Assistant3f1b696c

fix: tap-to-wake blocking and microphone sensitivity issuesb9e2e76e

fix: reduce noise suppression for better microphone sensitivitya62bbe43

fix: restore tap continue feedback sound (preserve functionality)12915bcd

refactor: optimize based on SDK analysis and conversation_app referencef9facd8d

refactor(movement): use SDK compose_world_offset for proper pose compositiona9461341

fix: enable face tracking by default and improve tap detection logging51ad4f0e

chore: bump version to 0.3.002640f6c

v0.4.0: Daemon stability fixes and microphone optimizationa33ba571

update __version__2be4f257

combined all reference-doc as one foldera5e1e063

feat: add Sendspin multi-room audio support (Phase 13)9793fadb

fix: reduce control loop frequency to prevent daemon crash in IDLE statebe89d684

fix: IDLE state should be completely still, restore face tracking fps4fa5aec3

feat: Sendspin自动发现，无需用户配置b15f94c8

fix: 人脸追踪Y轴偏移补偿，移除Sendspin发送逻辑5345c645

fix: 人脸追踪添加平滑过渡，避免抽搐式转头6efe6bdd

fix: Sendspin使用固定client_id和PLAYER角色，恢复原版人脸追踪参数a5465eb9

fix: Sendspin PLAYER角色需要player_support参数45977a5f

fix: 人脸追踪Y轴偏移补偿，看向眼睛而非脸部中心1adce2d5

fix: Noise suppression默认值改为15%ec996a5e

fix: Noise suppression启动时设置为15% (PP_MIN_NS=0.85)5254645b

debug: 添加人脸追踪调试日志，移除Y偏移，增加smoothing factor3f94c2a4

fix: 反转pitch方向，修复机器人向上看的问题8a00e9e2

debug: 暂时禁用face tracking smoothing进行调试1b2fe019

debug: 添加最终pose日志237ed8a1

fix: 修复人脸追踪偏上问题10a4ce76

fix: 修复Sendspin音频播放和人脸追踪平滑9106d0cb

fix: 修复euler顺序和Sendspin音频播放dadc0d2f

refactor: 使用SDK的compose_world_offset进行正确的pose组合5b55e2a9

fix: 添加人脸追踪pitch偏移补偿（向下7度）d032f095

fix: 修正pitch补偿方向（正值向下看）ddf4b258

fix: 添加yaw补偿（向左5度），修复机器人偏向用户右边的问题ce50e0c6

fix: 修正yaw补偿方向（-5度）3032377e

fix: 优化退出机制，减少shutdown超时477aeb20

调整人脸追踪补偿: pitch=9度(向下), yaw=-7度(向右)9dd9020e

feat: add scrollable changelog section to landing page19a2af66

feat: add scrollable changelog section to landing page739e3d5b

Merge branch 'main' of https://huggingface.co/spaces/djhui5710/reachy_mini_ha_voice319390f3

docs: update features and usage sections with new capabilities326e2ad7

fix: reduce tap-to-wake default threshold to 0.5g (most sensitive)7bddff72

fix: replace non-existent clear_output_buffer with stop_playinga04b2620

docs: update changelog with latest fixes4051ebdb

feat: add gesture detection (thumbs up, open palm) with MediaPipe91f738a5

feat: add more gestures (thumbs_down, fist, peace, ok, pointing_up)bf8cf179

docs: update PROJECT_PLAN.md with gesture detection (Phase 21)01429cd1

手势识别改用纯OpenCV实现，无额外依赖38eb7088

人脸模型下载加重试机制(3次重试，间隔5秒)e4d978cb

手势识别改用MediaPipe (0.10.31+支持numpy2)1865473b

手势识别增加到11种: thumbs_up/down, open_palm, fist, peace, pointing_up, ok, rock, call, three, fourb5ff72f7

v0.6.0: MediaPipe手势识别(11种手势)d2d97b83

更新文档: 手势识别增加到11种8a431566

手势识别改用纯OpenCV (ARM兼容，无MediaPipe依赖)211d747b

手势识别: ARM64自动安装mediapipe 0.10.18 (--no-deps避免numpy冲突)ac24fdc9

手势识别: 移除自动安装，无mediapipe时静默禁用585e14d9

手势识别: 首次运行自动安装mediapipe 0.10.18 (ARM64)606f861a

mediapipe依赖移到pyproject.toml，代码只安装mediapipe本身e1fb914b

恢复到4051ebd: 手势识别有依赖冲突，暂时移除c92d558e

人脸模型下载加重试机制(3次重试，间隔5秒)2f0e8683

优化人脸追踪资源使用: 自适应帧率ae100805

更新文档: 同步人脸追踪资源优化功能0361684b

Sendspin: 优先使用16kHz采样率(ReSpeaker原生支持)23c59a7a

修复: 语音助手唤醒时暂停Sendspin和音乐播放feebc51e

修复: tap_sensitivity默认值改为0.5g, 修复camera_server属性名83f2d5a0

持久化tap_sensitivity设置81ee9c6f

修复: Sendspin连接到music_player而非tts_playerab1716fe

docs: update changelog for v0.5.1 bug fixes5f422a0c

docs: translate PROJECT_PLAN.md to English91cfdeb6

docs: translate PROJECT_PLAN.md to English (complete)b10ca0f3

docs: update Technical Architecture diagram with full system overview33becb58

docs: fix STT/TTS engine description - user configured in HA94a04ed8

fix: allow tap to exit conversation without refractory delay4e1feee4

fix: send stop request to HA when exiting tap conversation mode916f7700

docs: rename project to 'Reachy Mini for Home Assistant'c5af1a90

fix: update emotion mapping to use available robot emotions1b8e11b6

fix: enable HA control of robot pose and fix continuous conversationaffc41bf

chore: bump version to v0.5.2c256ff2d

fix: improve continuous conversation with conversation_id tracking8a5ee8a7

chore: bump version to v0.5.3b03d17a3

fix: wait for RUN_END before starting new conversation05983437

chore: bump version to v0.5.490a9b9f5

fix: prevent concurrent pipelines and add prompt sound for continuous conversation8689b0f3

chore: bump version to v0.5.53bc695f9

fix: better pipeline state tracking to prevent duplicate audio300b49f0

chore: bump version to v0.5.68a1f05c1

feat: Add DOA turn-to-sound at wakeup (v0.5.7)d84e9370

fix: Remove speech_detected check in DOA turn-to-sound9a112461

fix: Change DOA turn-to-sound logs to INFO level for visibility10772b58

fix: Show raw DOA angle in Home Assistant (0-180)1b0c4060

fix: Invert DOA yaw direction - was turning opposite wayad7b805c

fix: EntityRegistry has no 'state' attribute - use server.state8d667cbe

fix: Add debug logging for noise suppression, fix PP_MIN_NN value9844c98f

fix: Disable tap detection during emotion playback to prevent false triggers17348fa2

v0.5.8: Fix tap detection during emotion playback - poll daemon API for move completionf7f01c88

v0.5.9: Default wake word to hey_reachy, fix wake word switching bug06a6f968

v0.5.10: Actually fix wake word switching - set id attribute on loaded models6ed5b093

v0.5.11: Reset feature extractors when switching wake words to prevent false triggers0e3f2eb7

Increase hey_reachy probability_cutoff to 0.9 to reduce false triggers91115a80

v0.5.12: Remove broken hey_reachy model, revert default to okay_nabud18707c0

Add retrained hey_reachy wake word modelce7697dd

v0.5.13: JSON-driven animation system + new landing page style12ab5fa7

Adjust animation parameters: idle=no movement, larger amplitudes, slower frequencies for smoother motion080e85ca

Increase control loop to 100Hz (daemon updated), adjust animation frequenciesfc9e96f4

Fix: Skip wake word detection when pipeline is active (prevents false triggers during conversation)f072078e

Fix: Eliminate race condition in pipeline state, adjust animation amplitudes to moderate level264db797

Fix: Skip ALL wake word processing (features + detection) when pipeline is active636fb5e7

Fix: Disable tap detection during conversation to prevent false triggers from robot movementa6cdaca5

Fix: Disable tap detection IMMEDIATELY in wakeup() and wakeup_from_tap() to prevent false triggers02197ff9

Add logging to debug tap detection disable7a7e15da

Speaking: pause face tracking, use lively nodding animation (1.5Hz)0813da7b

CRITICAL FIX: Rename duplicate _reachy_on_listening to _reachy_on_idle - tap detection was never re-enabledf493f8c9

v0.5.15: Audio settings persistence, Sendspin discovery refactor, tap detection fix99f80f85

Fix: asyncio.coroutine removed in Python 3.12, use Coroutine type hint66017677

Fix: PEP8 compliance and wake word refractory period after conversation ends5fb657a5

v0.5.16: Remove tap-to-wake, add Continuous Conversation switch20e58a2f

Fix: Ignore HA continue_conversation, only use our switch10f7c31b

Fix: Restore HA continue_conversation support, our switch is unconditional overrideeb57938d

refactor: 简化唤醒词检测逻辑，按照参考项目模式afdb99dc

debug: 添加说话动画的调试日志0d8fe982

debug: 将 Voice event 日志改为 INFO 级别88356b9a

improve: 增强说话动画幅度，更自然地模拟人类讲话96fa36a8

update index.html linkc299521c

improve: 改进说话动画，使用多频率振荡器模拟自然头部摆动b2996422

feat: 添加基于音频分析的说话动画d29db4bc

fix: 调整思考动画，减少向后仰头幅度e6a323c5

refactor: 移除硬编码动作，动画完全由JSON配置驱动581cea0d

fix: 移除音频预下载分析，使用JSON动画替代741db5c6

feat: 添加实时音频驱动的说话动画8fbc5536

release: v0.6.0 - 实时音频驱动说话动画13f074fa

remove unused file8fd6a8d5

fix: 使用固定大小音频块发送，提升STT响应速度c1478382

feat: 添加 hey_ree_che 唤醒词配置9aa7e2d0

fix: 修复stop词检测，设置stop_word的id属性a9c7d5d2

Upload hey_ree_che.tflite5c75d150

fix: 加载openWakeWord子目录中的唤醒词配置cbee241c

feat: prioritize MicroWakeWord over OpenWakeWord for same-name wake words327c6921

chore: bump version to 0.6.1, show only 6 changelog entries by defaultd5505b17

refactor: load changelog from JSON file dynamically14343987

docs: complete changelog history from v0.1.0 to v0.6.169d1b8f6

docs: update index.html - remove continuous conversation highlight, update entity count to 45+19d16742

docs: highlight Multi-room audio (Sendspin) in hero badges7f192be5

docs: change wake word example from Hey Jarvis to Hey Reeche6cbbe137

update model name3b97ed3c

remove duplicated wakeword0b44b9ba

feat: 添加手势识别功能 (HaGRID ONNX模型)47c5ba58

chore: 添加手势识别ONNX模型文件 (LFS)e4036622

fix: 修复手势检测结果不更新的问题5eb7a53b

fix: 修复DOA方向，减少语音日志输出579082ff

fix: 修复DOA方向, 减少日志, 添加手势检测调试5666e959

fix: 使用状态判断唤醒词检测, 添加手势模型信息日志5ce6940c

fix: 重写手势检测器，使用正确的模型输入输出格式273c2958

fix: 重写gesture_detector.py，修正模型输出格式e5e9146e

debug: 添加手势检测INFO日志e70c7348

debug: 添加手势检测循环确认日志d270f255

Debug: add hand detector raw output logging, lower thresholds to 0.31bb715fc

Fix: push gesture state to Home Assistant via callbackf45ab723

v0.6.2: Gesture detection with HaGRID ONNX models (18 gestures)b9abf97a

docs: add emoji gesture reference table26e543e4

Redesign landing page with Home Assistant blue theme422425ae

Add all referenced resources to links section7635cbd0

Add HaGRID dataset linkc53da401

Clarify: Reachy Mini app using ESPHome protocol, not ESPHome device9a84c9fd

Make hero badges more prominent with blue gradientc8977fbd

Move App Store link to links section30184399

Optimize: aggressive power saving when idle (0.5fps), gesture only with facee006bba1

docs: update changelog and PROJECT_PLAN with power optimization details78b72379

Fix: prevent wake word re-trigger during continuous conversation, reduce log spam7c7e79cf

fix: prevent wake word detection during TTS playback (v0.6.3)7c946878

fix: remove premature _tts_played reset in RUN_END (v0.6.4)cecb01dc

chore: correct version numbers - gesture is 0.7.0, current is 0.7.208a2d90b

fix: revert to reference project pattern for wake word detection (v0.7.3)9d926324

docs: sync documentation with code (100Hz control loop, 2fps idle camera)02470eda

replace the picture to video76f36286

Add YouTube video, dashboard card link, and video container stylesb2da21c9

Add Dashboard Card feature to Capabilities section01bcfe24

Enlarge hero section and video containerdfa674aa

chore: cleanup tap_detector residual code and update descriptions199ba1d1

Jan 16

Because the requested Python version (>=3.10) does not satisfy Python>=3.12 and aiosendspin>=2.0.1 depends on Python>=3.12, we can conclude that aiosendspin>=2.0.1 cannot be used.

fix: set python version to work with default envc5bd8c23

djhui5710 changed pull request status to merged Jan 17

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment