CarolinePascal
|
e2f3982e2c
|
style(config validation): storing microphone config validation in dedicated methods
|
2026-01-20 12:20:27 +01:00 |
|
CarolinePascal
|
a73ac2bdbb
|
[skip-ci] style(clean): cleaning up audio benchmark
|
2026-01-20 12:20:27 +01:00 |
|
CarolinePascal
|
95de732e55
|
[skip-ci] feat(multiprocess audio stream): running input audio stream in a separate process to avoid extensive CPU usage impacts
|
2026-01-20 12:20:27 +01:00 |
|
CarolinePascal
|
b2383236ca
|
[skip-ci] fix(audio buffers): fill audio buffers before entering the control loop to avoid first audio chunk reading delay
|
2026-01-20 12:20:27 +01:00 |
|
CarolinePascal
|
4b98cc25c8
|
[skip-ci] fix(async read): remove async read from LeKiwi to avoid delays
|
2026-01-20 12:20:27 +01:00 |
|
CarolinePascal
|
90780c4de8
|
[skip-ci] feat(portaudio timeout): decresing portaudio stream timeout for low latency
|
2026-01-20 12:20:27 +01:00 |
|
CarolinePascal
|
6f6e046c53
|
[skip-ci] feat(audio rerun): adding support for multiple channels visualization with rerun
|
2026-01-20 12:20:27 +01:00 |
|
CarolinePascal
|
8cd64eaad1
|
fix(resnet weights): fix default ResNet weights for audio
|
2026-01-20 12:20:27 +01:00 |
|
CarolinePascal
|
e620395416
|
feat(init audio buffer): adding a separate parameter for the initial audio buffer size
|
2026-01-20 12:20:27 +01:00 |
|
CarolinePascal
|
0fbcbcdb2e
|
feat(audio ACT): removing normalization and pretrained weights because it does not really make sense
|
2026-01-20 12:20:26 +01:00 |
|
CarolinePascal
|
674f5dfd75
|
test(audio frame): fixing decoded audio frame shape
|
2026-01-20 12:20:26 +01:00 |
|
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
|
59e8f4572c
|
[skip-ci] fix(typo): fixing microphone key typo in audio benchmark
|
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
|
bf8ede852d
|
fix(busy wait): removing busy_wait on MacOS for python>3.11
|
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
|
e714ff22e2
|
[skip ci] doc(benchmark): adding microphones recording benchmark
|
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
|
a4d4ef0e7f
|
fix: fixing typos
|
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
|
0a6ca58299
|
fix: adding proper definition for "total_audio" in LeRobotDataset
|
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 |
|