compact UI: remove instrumental checkbox, lock steps, scroll fix, timing labels, LoRA+LM same row

default 200 epochs, label with timing info, instant cancel in preprocessing

instant cancel during preprocessing (dont wait for thread to finish)

fix: parse multipart/mixed response from /understand (was expecting JSON, got multipart)

fix LM caption: use poll response data directly, empty body from /job?result=1 was the bug

debug LM caption: log result keys, check nested result, increase fetch timeout to 120s

fix: 5h fixed timeout per file, check total feasibility first

LM captioning: 5h timeout per file, check feasibility before starting

zip download: LoRA adapter + generated captions bundled together

wire fast captioning (CLAP+Whisper+VAD) into training, add LM caption checkbox

random 60s crop at training time (matches Side-Step chunk-duration), remove pre-split chunking

audio-level chunking (not latent), auto-scale epochs for chunk count

chunk latents into ~30s segments for faster CPU training, energy-aware boundaries

default rank 16 for faster CPU training

add credit lines to both tabs

compact Generate Music UI, same layout style as Train tab

move audio upload to left column

skip bare librosa sidecar, let preprocessing faf analysis handle caption fallback

fix adapter save path, smart LM fallback, compact training UI, remove Server Status

cancel, captioning, preprocessing, sidecar upload, elapsed time, GeneratorExit fix

fix review: debug leak, int crash, rank mismatch, 0-byte skip, log cap, understand diag

fix: save PEFT adapter (not full model), remove random suffix from LoRA names, fix epoch cap to 1000

fix: save_every_n_epochs=0, add demucs-infer to Dockerfile, debug adapter dir

fix all review issues: dedup sampling/unwrap, thread-safe lock, cleanup, retry, security docs

add _is_space flag, block inference during training, understand clone fix

major update: PyTorch inference, Gradio 6, session isolation, /understand captioning

truncate long files to fit cap, show which files truncated/skipped

accept files until total audio cap reached, skip rest with warning

replace per-file cap with total audio cap (30 min max)

add LoRA download button after training (gr.File output, like rvc-beatrice)

remove ace-server understand proxy, captioning stays librosa + txt sidecars

add /understand API endpoint for GGUF audio captioning

update defaults: LR 3e-4, rank 32, alpha 2x rank (per Side-Step author)

save only on cancel/finish, max epochs 1000, default 3

switch training to standard turbo (11s/epoch), auto-select standard GGUF for LoRA inference

fix: train on XL turbo (matches XL GGUF for inference), add XL checkpoint download

allow custom LoRA values in dropdown (API clients)

log ace-server restart, show output for adapter debugging

fix: forward adapter to synth request, default LM to 1.7B

fix: adapter saved to clean dir, LM dropdown no 'Default', on-demand download

Side-Step training engine, tested locally on CPU

add LoRA adapter dropdown to inference UI

default mp3, remove format selector, increase LM timeout to 900s

remove accelerate (causes meta tensors), clean up patches

fix meta tensor crash: force low_cpu_mem_usage=False and float32 for CPU

disable flash_sdp on CPU, force attn_implementation=sdpa for training

add granular logging + full stderr to diagnose preprocessing hang

fix: use float32 not bfloat16 for CPU training (bf16 deadlocks on CPU)

redirect training subprocess stderr to log file for debugging

run training as detached subprocess to survive Gradio session timeout