CarolinePascal
7d430c8067
style(return types): adding missing return types
2026-01-20 12:20:26 +01:00
CarolinePascal
5f114c1d74
feat(init audio buffers): adding correct audio buffer initialization with actually recorded background noise instead of pure silence
2026-01-20 12:20:26 +01:00
CarolinePascal
ad01ef19f4
fix(audio buffers): add security crop to avoid audio buffer overfilling
2026-01-20 12:20:26 +01:00
CarolinePascal
97e91698fb
[skip-ci] fix(online audio chunks): adding missing observation copy when adding audio buffer
2026-01-20 12:20:26 +01:00
CarolinePascal
af0294198a
[skip ci] feat(visualize audio): adding audio recordings visualization in rerun
2026-01-20 12:20:22 +01:00
CarolinePascal
421fdcce96
[skip ci] fix(audio latency): setting microphone recording latency to low as default
2026-01-20 12:12:59 +01:00
CarolinePascal
bb63ad9715
fix(online audio chunks): querying audio chunks as a shifting widow over previous audio samples to match the default audio chunk size
2026-01-20 12:12:59 +01:00
CarolinePascal
3c90a79c57
feat(audio in ACT): adding audio features support in ACT using mel-spectrogram representation
2026-01-20 12:12:59 +01:00
CarolinePascal
8e29c530ed
fix(pytorch audio format): switching to pytorch's default channel first format for audio
2026-01-20 12:12:59 +01:00
CarolinePascal
b573b7a052
fix(audio decoding): fixing edge cases where the requested audio chunk starts before the beginning of the recording
2026-01-20 12:12:59 +01:00
CarolinePascal
926184110b
feat(audio in policies): adding audio as a input feature in policies
2026-01-20 12:12:59 +01:00
CarolinePascal
f73db4394b
fix(audio chunks): querying audio chunks in the past rather than in the future
2026-01-20 12:12:59 +01:00
CarolinePascal
bff91f9927
feat(torchcodec): setting torchcodec as default as the new official release supports audio decoding
2026-01-20 12:12:59 +01:00
CarolinePascal
6d726266fd
fix(audio load file): adding missing dimension when loading mono audio data
2026-01-20 12:12:59 +01:00
CarolinePascal
2962330bb1
style(imports): simplify soundfile imports
2026-01-20 12:12:59 +01:00
CarolinePascal
067993bb11
fix(typos): fixing typos
2026-01-20 12:12:58 +01:00
CarolinePascal
e4dd00c8f5
fix(audio feature shape): fixing audio feature shape ordering (frames first, channels second)
2026-01-20 12:12:58 +01:00
CarolinePascal
3bbd161cfd
[skip ci] feat(audio recording): adding new asyn start_recording, stop_recording and read functions to avoid for loop delays
2026-01-20 12:12:58 +01:00
CarolinePascal
6d7be63f59
[skip ci] fix(wav format): fix default WAV format for audio storage
2026-01-20 12:12:58 +01:00
CarolinePascal
b9d0dfb9a2
[skip ci] refactor(Microphone class): properly rename Microphone class to PortAudioMicrophone to avoid conflicts with the eponym base class
2026-01-20 12:12:58 +01:00
CarolinePascal
dce483060f
[skip ci] feat(audio recording): handle folder creation in start_recording directly
2026-01-20 12:12:58 +01:00
CarolinePascal
c32b9182d9
[skip ci] feat(torchcodec): adding support for torchcodec audio decoding
2026-01-20 12:12:58 +01:00
CarolinePascal
9a5c96b2b1
fix: fixing issue with microphone channels numbering and status recovery on stop_recording
2026-01-20 12:12:58 +01:00
CarolinePascal
688195fc46
docs: add methods descriptions and comments on tricky parts
2026-01-20 12:12:58 +01:00
CarolinePascal
99eb0bbafc
Adding last missing audio features in LeRobotDataset
2026-01-20 12:12:58 +01:00
CarolinePascal
16de8b3f19
Adding support for audio data recording and broadcasting for LeKiwi
2026-01-20 12:12:55 +01:00
CarolinePascal
580008663b
Adding flag for file writting recording case
2026-01-20 12:12:07 +01:00
CarolinePascal
52c424c5eb
Adding multiprocessing support for audio recording
2026-01-20 12:12:07 +01:00
CarolinePascal
836195e59c
Renamming sampling rate to sample rate for consistency
2026-01-20 12:12:07 +01:00
CarolinePascal
be09a59e05
Adding audio tests
2026-01-20 12:12:03 +01:00
CarolinePascal
373a169bd2
Fixing sounddevice stream active state recovery and adding corresponding exceptions
2026-01-20 12:10:45 +01:00
CarolinePascal
00536c6c5b
Adding missing features for audio frames verification and stats
2026-01-20 12:10:45 +01:00
CarolinePascal
cdd3a859ef
Adding pytorch compatible conversion for audio
2026-01-20 12:10:45 +01:00
CarolinePascal
5276fc0d6f
Remove variable audio recordings data types (will be converted to float32 anyway)
2026-01-20 12:10:45 +01:00
CarolinePascal
6a2882f978
Adding audio frames reading capability
2026-01-20 12:10:37 +01:00
CarolinePascal
8874547353
Adding microphone recording in control loop
2026-01-20 12:10:12 +01:00
CarolinePascal
2864caad80
Adding audio modality in LeRobotDatasets
2026-01-20 12:10:12 +01:00
CarolinePascal
d998660aa1
Integrate microphones in Robot class
2026-01-20 12:10:09 +01:00
CarolinePascal
7e5f3b35e9
Implementing basic integration of microphones using soundfile and sounddevice
2026-01-20 12:08:27 +01:00
Alexis D
13bfee1aa4
Set 10 direction bit for Current Load attribute ( #1014 )
2026-01-20 11:20:30 +01:00
Jade Choghari
79688a09f2
improve(dataset-tools): image2video editing tools : Multiple episodes per video file ( #2811 )
...
* improve image2video
* add episodes video encoding
* fix mypy failing
* iterate on review
* nit
* remove max, and let it be optional
* iterate more
* update docs
* fix test
---------
Co-authored-by: Michel Aractingi <michel.aractingi@huggingface.co >
2026-01-20 11:04:22 +01:00
Francesco Capuano
b2ff219624
Fixes aggregation of image datasets ( #2717 )
...
* fix: use features when aggregating image based datasets
* add: test asserting for data type
* add: features param to writing dataset
---------
Co-authored-by: Steven Palma <imstevenpmwork@ieee.org >
2026-01-19 23:36:41 +01:00
Maximilian Ofir
66929c5935
feat: add async server-client streaming support for Groot policy ( #2812 )
2026-01-19 22:13:48 +01:00
Steven Palma
5286ef8439
feat(utils): extend import check util ( #2820 )
...
* refactor(utils): is_package_available now differentiate between pkg name and module name
* refactor(tests): update require_package decorator
2026-01-19 16:43:11 +01:00
bigmbigk
fe068df711
fix(train): eval env initialization on train script ( #2818 )
...
* fix: eval env initialization on train script
Signed-off-by: bigmbigk <bigmbigk@gmail.com >
* fix: eval env creation condition
---------
Signed-off-by: bigmbigk <bigmbigk@gmail.com >
2026-01-19 14:14:10 +01:00
Sung-Wook Lee
da41646073
fix libero reset logic for correct resetting ( #2817 )
2026-01-19 13:18:52 +01:00
Steven Palma
46e19ae579
feat: is connect checks decorators ( #2813 )
2026-01-16 18:52:06 +01:00
Alex Tyshka
77dc49b3a3
Fix delta timestamps with episodes filter and add tests ( #2612 )
2026-01-16 18:14:54 +01:00
Alex Tyshka
33910673ec
Bugfix: Add tests for image deletion and fix mixed image-video deletion ( #2592 )
...
* Add tests for image deletion and fix mixed-image-video deletion
* Fix docstring whitespace
* Remove debug print
Signed-off-by: Alex Tyshka <atyshka15@gmail.com >
* Remove inaccurate comment
* Remove batched video test
---------
Signed-off-by: Alex Tyshka <atyshka15@gmail.com >
2026-01-16 18:14:15 +01:00
Michel Aractingi
19dce78457
Refactor: Move PEFT config from training script to policy level ( #2806 )
...
* move peft config from `lerobot_train` to policy level
* Update src/lerobot/scripts/lerobot_train.py
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com >
Signed-off-by: Michel Aractingi <michel.aractingi@huggingface.co >
* copilot response
* Change the polciy function to return targets rather than peft config.`_get_default_peft_targets()` override in PI0, PI0.5, SmolVLA
* remove none check when building config dict
---------
Signed-off-by: Michel Aractingi <michel.aractingi@huggingface.co >
2026-01-16 17:14:28 +01:00
