Mirror complete Google Drive artifacts and document all released variants

.gitattributes

@@ -33,3 +33,240 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gBR_sBM_c01_d04_mBR0_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gBR_sBM_c01_d04_mBR0_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gBR_sBM_c01_d05_mBR0_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gBR_sBM_c01_d05_mBR0_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gHO_sBM_c01_d20_mHO5_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gHO_sBM_c01_d21_mHO5_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gJB_sBM_c01_d08_mJB5_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gJB_sBM_c01_d09_mJB5_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gJS_sBM_c01_d01_mJS3_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gJS_sBM_c01_d01_mJS3_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gJS_sBM_c01_d03_mJS3_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gJS_sBM_c01_d03_mJS3_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gKR_sBM_c01_d28_mKR2_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gKR_sBM_c01_d28_mKR2_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gKR_sBM_c01_d30_mKR2_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gKR_sBM_c01_d30_mKR2_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gLH_sBM_c01_d17_mLH4_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gLH_sBM_c01_d17_mLH4_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gLH_sBM_c01_d18_mLH4_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gLH_sBM_c01_d18_mLH4_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gLO_sBM_c01_d13_mLO2_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gLO_sBM_c01_d13_mLO2_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gLO_sBM_c01_d15_mLO2_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gLO_sBM_c01_d15_mLO2_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gMH_sBM_c01_d22_mMH3_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gMH_sBM_c01_d22_mMH3_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gMH_sBM_c01_d24_mMH3_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gMH_sBM_c01_d24_mMH3_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gPO_sBM_c01_d10_mPO1_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gPO_sBM_c01_d10_mPO1_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gPO_sBM_c01_d11_mPO1_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gPO_sBM_c01_d11_mPO1_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gWA_sBM_c01_d25_mWA0_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gWA_sBM_c01_d25_mWA0_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gWA_sBM_c01_d26_mWA0_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/full/300ksteps/gWA_sBM_c01_d26_mWA0_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/full/wandb/run-20251202_121332-lc8aneeb/files/output.log filter=lfs diff=lfs merge=lfs -text
+models/full/wandb/run-20251202_121332-lc8aneeb/logs/debug-internal.log filter=lfs diff=lfs merge=lfs -text
+models/full/wandb/run-20251202_121332-lc8aneeb/run-lc8aneeb.wandb filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gBR_sBM_c01_d04_mBR0_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gBR_sBM_c01_d04_mBR0_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gBR_sBM_c01_d05_mBR0_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gBR_sBM_c01_d05_mBR0_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gHO_sBM_c01_d20_mHO5_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gHO_sBM_c01_d21_mHO5_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gJB_sBM_c01_d08_mJB5_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gJB_sBM_c01_d09_mJB5_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gJS_sBM_c01_d01_mJS3_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gJS_sBM_c01_d01_mJS3_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gJS_sBM_c01_d03_mJS3_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gJS_sBM_c01_d03_mJS3_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gKR_sBM_c01_d28_mKR2_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gKR_sBM_c01_d28_mKR2_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gKR_sBM_c01_d30_mKR2_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gKR_sBM_c01_d30_mKR2_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gLH_sBM_c01_d17_mLH4_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gLH_sBM_c01_d17_mLH4_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gLH_sBM_c01_d18_mLH4_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gLH_sBM_c01_d18_mLH4_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gLO_sBM_c01_d13_mLO2_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gLO_sBM_c01_d13_mLO2_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gLO_sBM_c01_d15_mLO2_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gLO_sBM_c01_d15_mLO2_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gMH_sBM_c01_d22_mMH3_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gMH_sBM_c01_d22_mMH3_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gMH_sBM_c01_d24_mMH3_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gMH_sBM_c01_d24_mMH3_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gPO_sBM_c01_d10_mPO1_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gPO_sBM_c01_d10_mPO1_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gPO_sBM_c01_d11_mPO1_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gPO_sBM_c01_d11_mPO1_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gWA_sBM_c01_d25_mWA0_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gWA_sBM_c01_d25_mWA0_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gWA_sBM_c01_d26_mWA0_ch02_1.wav filter=lfs diff=lfs merge=lfs -text
+models/without_motioinbert/300ksteps/gWA_sBM_c01_d26_mWA0_ch02_2.wav filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gBR_sBM_c01_d04_mBR0_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gBR_sBM_c01_d04_mBR0_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gBR_sBM_c01_d05_mBR0_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gBR_sBM_c01_d05_mBR0_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gHO_sBM_c01_d20_mHO5_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gHO_sBM_c01_d21_mHO5_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gJB_sBM_c01_d08_mJB5_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gJB_sBM_c01_d09_mJB5_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gJS_sBM_c01_d01_mJS3_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gJS_sBM_c01_d01_mJS3_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gJS_sBM_c01_d03_mJS3_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gJS_sBM_c01_d03_mJS3_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gKR_sBM_c01_d28_mKR2_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gKR_sBM_c01_d28_mKR2_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gKR_sBM_c01_d30_mKR2_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gKR_sBM_c01_d30_mKR2_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gLH_sBM_c01_d17_mLH4_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gLH_sBM_c01_d17_mLH4_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gLH_sBM_c01_d18_mLH4_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gLH_sBM_c01_d18_mLH4_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gLO_sBM_c01_d13_mLO2_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gLO_sBM_c01_d13_mLO2_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gLO_sBM_c01_d15_mLO2_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gLO_sBM_c01_d15_mLO2_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gMH_sBM_c01_d22_mMH3_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gMH_sBM_c01_d22_mMH3_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gMH_sBM_c01_d24_mMH3_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gMH_sBM_c01_d24_mMH3_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gPO_sBM_c01_d10_mPO1_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gPO_sBM_c01_d10_mPO1_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gPO_sBM_c01_d11_mPO1_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gPO_sBM_c01_d11_mPO1_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gWA_sBM_c01_d25_mWA0_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gWA_sBM_c01_d25_mWA0_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gWA_sBM_c01_d26_mWA0_ch02_1_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/AudioLDM[[:space:]](default)/gWA_sBM_c01_d26_mWA0_ch02_2_default.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gBR_sBM_c01_d04_mBR0_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gBR_sBM_c01_d04_mBR0_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gBR_sBM_c01_d05_mBR0_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gBR_sBM_c01_d05_mBR0_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gHO_sBM_c01_d20_mHO5_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gHO_sBM_c01_d21_mHO5_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gJB_sBM_c01_d08_mJB5_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gJB_sBM_c01_d09_mJB5_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gJS_sBM_c01_d01_mJS3_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gJS_sBM_c01_d01_mJS3_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gJS_sBM_c01_d03_mJS3_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gJS_sBM_c01_d03_mJS3_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gKR_sBM_c01_d28_mKR2_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gKR_sBM_c01_d28_mKR2_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gKR_sBM_c01_d30_mKR2_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gKR_sBM_c01_d30_mKR2_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gLH_sBM_c01_d17_mLH4_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gLH_sBM_c01_d17_mLH4_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gLH_sBM_c01_d18_mLH4_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gLH_sBM_c01_d18_mLH4_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gLO_sBM_c01_d13_mLO2_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gLO_sBM_c01_d13_mLO2_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gLO_sBM_c01_d15_mLO2_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gLO_sBM_c01_d15_mLO2_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gMH_sBM_c01_d22_mMH3_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gMH_sBM_c01_d22_mMH3_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gMH_sBM_c01_d24_mMH3_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gMH_sBM_c01_d24_mMH3_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gPO_sBM_c01_d10_mPO1_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gPO_sBM_c01_d10_mPO1_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gPO_sBM_c01_d11_mPO1_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gPO_sBM_c01_d11_mPO1_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gWA_sBM_c01_d25_mWA0_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gWA_sBM_c01_d25_mWA0_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gWA_sBM_c01_d26_mWA0_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ground[[:space:]]Truth/gWA_sBM_c01_d26_mWA0_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gBR_sBM_c01_d04_mBR0_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gBR_sBM_c01_d04_mBR0_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gBR_sBM_c01_d05_mBR0_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gBR_sBM_c01_d05_mBR0_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gHO_sBM_c01_d20_mHO5_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gHO_sBM_c01_d21_mHO5_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gJB_sBM_c01_d08_mJB5_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gJB_sBM_c01_d09_mJB5_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gJS_sBM_c01_d01_mJS3_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gJS_sBM_c01_d01_mJS3_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gJS_sBM_c01_d03_mJS3_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gJS_sBM_c01_d03_mJS3_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gKR_sBM_c01_d28_mKR2_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gKR_sBM_c01_d28_mKR2_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gKR_sBM_c01_d30_mKR2_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gKR_sBM_c01_d30_mKR2_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gLH_sBM_c01_d17_mLH4_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gLH_sBM_c01_d17_mLH4_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gLH_sBM_c01_d18_mLH4_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gLH_sBM_c01_d18_mLH4_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gLO_sBM_c01_d13_mLO2_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gLO_sBM_c01_d13_mLO2_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gLO_sBM_c01_d15_mLO2_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gLO_sBM_c01_d15_mLO2_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gMH_sBM_c01_d22_mMH3_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gMH_sBM_c01_d22_mMH3_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gMH_sBM_c01_d24_mMH3_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gMH_sBM_c01_d24_mMH3_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gPO_sBM_c01_d10_mPO1_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gPO_sBM_c01_d10_mPO1_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gPO_sBM_c01_d11_mPO1_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gPO_sBM_c01_d11_mPO1_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gWA_sBM_c01_d25_mWA0_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gWA_sBM_c01_d25_mWA0_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gWA_sBM_c01_d26_mWA0_ch02_1.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Li[[:space:]]et[[:space:]]al./gWA_sBM_c01_d26_mWA0_ch02_2.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gBR_sBM_c01_d04_mBR0_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gBR_sBM_c01_d04_mBR0_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gBR_sBM_c01_d05_mBR0_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gBR_sBM_c01_d05_mBR0_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gHO_sBM_c01_d20_mHO5_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gHO_sBM_c01_d21_mHO5_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gJB_sBM_c01_d08_mJB5_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gJB_sBM_c01_d09_mJB5_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gJS_sBM_c01_d01_mJS3_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gJS_sBM_c01_d01_mJS3_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gJS_sBM_c01_d03_mJS3_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gJS_sBM_c01_d03_mJS3_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gKR_sBM_c01_d28_mKR2_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gKR_sBM_c01_d28_mKR2_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gKR_sBM_c01_d30_mKR2_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gKR_sBM_c01_d30_mKR2_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gLH_sBM_c01_d17_mLH4_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gLH_sBM_c01_d17_mLH4_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gLH_sBM_c01_d18_mLH4_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gLH_sBM_c01_d18_mLH4_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gLO_sBM_c01_d13_mLO2_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gLO_sBM_c01_d13_mLO2_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gLO_sBM_c01_d15_mLO2_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gLO_sBM_c01_d15_mLO2_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gMH_sBM_c01_d22_mMH3_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gMH_sBM_c01_d22_mMH3_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gMH_sBM_c01_d24_mMH3_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gMH_sBM_c01_d24_mMH3_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gPO_sBM_c01_d10_mPO1_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gPO_sBM_c01_d10_mPO1_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gPO_sBM_c01_d11_mPO1_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gPO_sBM_c01_d11_mPO1_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gWA_sBM_c01_d25_mWA0_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gWA_sBM_c01_d25_mWA0_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gWA_sBM_c01_d26_mWA0_ch02_1_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours/gWA_sBM_c01_d26_mWA0_ch02_2_pretrained.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gBR_sBM_c01_d04_mBR0_ch02_1_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gBR_sBM_c01_d04_mBR0_ch02_2_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gBR_sBM_c01_d05_mBR0_ch02_1_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gBR_sBM_c01_d05_mBR0_ch02_2_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gHO_sBM_c01_d20_mHO5_ch02_1_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gHO_sBM_c01_d21_mHO5_ch02_1_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gJB_sBM_c01_d08_mJB5_ch02_1_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gJB_sBM_c01_d09_mJB5_ch02_1_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gJS_sBM_c01_d01_mJS3_ch02_1_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gJS_sBM_c01_d01_mJS3_ch02_2_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gJS_sBM_c01_d03_mJS3_ch02_1_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gJS_sBM_c01_d03_mJS3_ch02_2_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gKR_sBM_c01_d28_mKR2_ch02_1_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gKR_sBM_c01_d28_mKR2_ch02_2_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gKR_sBM_c01_d30_mKR2_ch02_1_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gKR_sBM_c01_d30_mKR2_ch02_2_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gLH_sBM_c01_d17_mLH4_ch02_1_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text
+testsets_video_results/Ours[[:space:]](w-o[[:space:]]Contrastive[[:space:]]Pretraining)/gLH_sBM_c01_d17_mLH4_ch02_2_baseline-400k.mp4 filter=lfs diff=lfs merge=lfs -text

README.md

@@ -14,7 +14,7 @@ tags:
 
 # AudioLDM-ControlNet
 
-Official model checkpoint for the paper:
+Official checkpoints and evaluation artifacts for the paper:
 
 **Dance to Music Generation leveraging Pre-training with Unpaired data and Contrastive Alignment**
 
@@ -30,22 +30,82 @@ AudioLDM-ControlNet is a dance-conditioned music generation model. It combines:
 2. beat-guided contrastive pretraining for cross-modal alignment, and
 3. a ControlNet-style conditioning module built on an AudioLDM backbone.
 
-The released checkpoint corresponds to the **full model** reported in the paper.
+This repository includes the **full model**, the **w/o MotionBERT** checkpoint,
+and the complete artifact collection previously shared on
+[Google Drive](https://drive.google.com/drive/folders/1rhDqPitcFlthedr5vS6kG2PoNO_PW2it?usp=sharing).
 
 ## Repository Contents
 
-The following files are stored in the root of this model repository:
+The original Google Drive directory structure is preserved under `models/` and
+`testsets_video_results/`. Only macOS `.DS_Store` metadata files are omitted.
 
-| File | Description |
+| Path | Contents |
 | --- | --- |
-| `checkpoint-global_step=299999.ckpt` | Full AudioLDM-ControlNet model checkpoint at training step 299999 |
-| `audioldm_original_medium_stretch_pretrained.yaml` | Model and preprocessing configuration corresponding to the checkpoint |
+| [`models/full/`](tree/main/models/full) | Full-model checkpoint, YAML configuration, 36 generated WAV files and `metrics.txt` in `300ksteps/`, and the original W&B training run in `wandb/` |
+| [`models/without_motioinbert/`](tree/main/models/without_motioinbert) | w/o MotionBERT checkpoint, YAML configuration, and 36 generated WAV files and `metrics.txt` in `300ksteps/` |
+| [`testsets_video_results/`](tree/main/testsets_video_results) | 216 MP4 comparison videos: 36 clips for each of the six conditions listed below |
+| `checkpoint-global_step=299999.ckpt` | Original root-level full-model checkpoint, retained for existing download links |
+| `audioldm_original_medium_stretch_pretrained.yaml` | Original root-level full-model configuration, retained for existing download links |
+
+The spelling `without_motioinbert` is retained from the original archive.
+The root-level checkpoint and configuration are identical to their counterparts
+under `models/full/`.
+
+Both checkpoints are named `checkpoint-global_step=299999.ckpt` and are stored
+in their respective variant's `checkpoints/` directory. The matching
+configurations are:
+
+- Full model: `models/full/audioldm_original_medium_stretch_pretrained.yaml`
+- w/o MotionBERT: `models/without_motioinbert/audioldm_original_medium_stretch_wo_mb.yaml`
+
+The six video folders are `AudioLDM (default)`, `Ground Truth`, `Li et al.`,
+`Ours`, `Ours (w-o Contrastive Pretraining)`, and `Ours (w-o MotionBERT)`.
+The w/o Contrastive Pretraining variant is represented by comparison videos;
+a checkpoint for that variant was not included in the Google Drive archive.
+
+## Download and Use
+
+Install the Hugging Face CLI if needed:
+
+```bash
+pip install -U huggingface_hub
+```
+
+Download the complete archived collection (approximately 16.5 GB), preserving
+its directory structure and avoiding a second local copy of the root checkpoint:
+
+```bash
+hf download kmraven/AudioLDM-ControlNet \
+  --include "models/*" --include "testsets_video_results/*" \
+  --local-dir data/releases/AudioLDM-ControlNet
+```
+
+To download only the full-model checkpoint and configuration:
+
+```bash
+hf download kmraven/AudioLDM-ControlNet \
+  "models/full/checkpoints/checkpoint-global_step=299999.ckpt" \
+  "models/full/audioldm_original_medium_stretch_pretrained.yaml" \
+  --local-dir data/releases/AudioLDM-ControlNet
+```
+
+Run preprocessing and evaluation with the
+[official source code and setup instructions](https://github.com/kmraven/AudioLDM-ControlNet#data-and-checkpoints).
+These are project-specific PyTorch Lightning checkpoints; use the repository's
+evaluation scripts. The archived YAML files preserve the original training
+settings and relative paths. Dataset inputs and separately referenced upstream
+weights must be prepared as described in the source repository. The archive
+does not include a standalone Stage 1 `model_best.pth` checkpoint.
+
+Exact training resume, including optimizer state and global step, may be
+incompatible with the refactored modules. If exact resume fails, the source
+repository recommends commit `0c1f4e3197a7c339586ce5769c6a4510dfbc6f30`.
 
 ## Checkpoint Details
 
 - Framework: PyTorch / PyTorch Lightning
 - Checkpoint format: `.ckpt`
-- Paper variant: Full model
+- Paper variants with checkpoints: Full model and w/o MotionBERT
 - Training step: 299999
 - Audio sampling rate: 16 kHz
 - Motion input frame rate: 60 FPS

models/full/300ksteps/gBR_sBM_c01_d04_mBR0_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1ae0bb99428a8105c48285cc5d5f5a3d66963922259d63b1722172a17bc4e8f
+size 163948

models/full/300ksteps/gBR_sBM_c01_d04_mBR0_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:110b2004e84e7c2b9e7331464d45974f1b0698574d65f41090fefc252f68125b
+size 163948

models/full/300ksteps/gBR_sBM_c01_d05_mBR0_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8acbf8b4fe7cc3641986ea0d2b7bf293203e69fe6a8e75bef016d5b205b5d633
+size 163948

models/full/300ksteps/gBR_sBM_c01_d05_mBR0_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f81d065b1e578738bc88769a15f0f2b5783683c7e64dc07faede5efe4fe84430
+size 163948

models/full/300ksteps/gHO_sBM_c01_d20_mHO5_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f5327ea788df2cfe3cd0df4552356031a2adb2da2a35d57892b7d5fdfcfb601
+size 163948

models/full/300ksteps/gHO_sBM_c01_d21_mHO5_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96aa47f8e6713005ab45a64d9c4dee4052db4e1727f0e29338c0e1732158dfe1
+size 163948

models/full/300ksteps/gJB_sBM_c01_d08_mJB5_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29a6c58734629b3e4352d52145dbc53077adf004f97a9d144aeef16cd9090b9a
+size 163948

models/full/300ksteps/gJB_sBM_c01_d09_mJB5_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a55f8948b7a27ab07f8040c813ab0900834311efd6c2240804d495a57584f9
+size 163948

models/full/300ksteps/gJS_sBM_c01_d01_mJS3_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fda374a518307410741e60955d8814ab100685f3c72205c8efc94679b3bcae8c
+size 163948

models/full/300ksteps/gJS_sBM_c01_d01_mJS3_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9dcf569290d58ce415bc1984b7ab6bfa272738600bfcb2084f427d54c3cba5d
+size 163948

models/full/300ksteps/gJS_sBM_c01_d03_mJS3_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3053c25583ef6925d916c1a6d4e5815e4933f1b33661a2d42f15172d97d44019
+size 163948

models/full/300ksteps/gJS_sBM_c01_d03_mJS3_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec400cf85c30f05c6cc6992a094e26ffd2381fa53ad17edb257a892f646ea9f6
+size 163948

models/full/300ksteps/gKR_sBM_c01_d28_mKR2_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5f1387242b3d2888e6bae09bf72334b1309dee3c44f8987d081d08dcfe12672
+size 163948

models/full/300ksteps/gKR_sBM_c01_d28_mKR2_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3abdafb876aa547f456837b570fb30f8586c88eddd886451468c93889da38533
+size 163948

models/full/300ksteps/gKR_sBM_c01_d30_mKR2_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffca146984ebe5b2ae58832d539e79a6b1c336e2e7c9c9c8bf60f2074c4ff201
+size 163948

models/full/300ksteps/gKR_sBM_c01_d30_mKR2_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:473a393c29b52f1c7504aa68d3e3a6a584614708741548fff2ac080c679753de
+size 163948

models/full/300ksteps/gLH_sBM_c01_d17_mLH4_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d870a73205362f7981d783eac65f2397640055b54502f6731b3a4f32cbdb0e1c
+size 163948

models/full/300ksteps/gLH_sBM_c01_d17_mLH4_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2185aaaccb78a37e96c5a9c91f321273cd3b267e7f8c63023d0bef6e9fa1aa45
+size 163948

models/full/300ksteps/gLH_sBM_c01_d18_mLH4_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f6776c2eb3a2563e52deae92906ab1a3bf799466c0ec37e0e40054479a89235
+size 163948

models/full/300ksteps/gLH_sBM_c01_d18_mLH4_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:80729ca1ebf8d0754ed189021d4b2d5a0a83ed24afffa664a641dbedcc6dd9a2
+size 163948

models/full/300ksteps/gLO_sBM_c01_d13_mLO2_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9f99639425ef5c244ded5e46363c203cfd28c46c82634335d134e9e2134c76f
+size 163948

models/full/300ksteps/gLO_sBM_c01_d13_mLO2_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32c5318695cd9de0e88b49977b378444eab6b1992cca11cd374475b74a048cc2
+size 163948

models/full/300ksteps/gLO_sBM_c01_d15_mLO2_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04ae467795db8a4a0eea7ae87c10aa0ad05d1fe438c6f510e6ea76871afcc693
+size 163948

models/full/300ksteps/gLO_sBM_c01_d15_mLO2_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3ad1b7f53f99cd4df3143a917cff002303b6000be41fc7bd1222a908ba8318f
+size 163948

models/full/300ksteps/gMH_sBM_c01_d22_mMH3_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:120fa1f45db863614cff34697747b9a88378550c29e4d7a7081013aa90280ffa
+size 163948

models/full/300ksteps/gMH_sBM_c01_d22_mMH3_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9af8873fb3f12360d5c8134aa26f5dd6a8451006b4f5f1cd663b9afcde742f41
+size 163948

models/full/300ksteps/gMH_sBM_c01_d24_mMH3_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06bf1e46d838d64ef2a1280d1d73ff8fb73b60887d6c0ee5f54b53a33a35e334
+size 163948

models/full/300ksteps/gMH_sBM_c01_d24_mMH3_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0732853c8f004d6e80e6bac64d62ca72ab829e315a48f4c3c6b474db596d91fd
+size 163948

models/full/300ksteps/gPO_sBM_c01_d10_mPO1_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54d0fe3b07873681e5e9ca15cf99195f768317948ad97495fe3827a108920a20
+size 163948

models/full/300ksteps/gPO_sBM_c01_d10_mPO1_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9444d73399b32a43d6be77f5dbea008f9107cab5b4180b765242a31823db2a6b
+size 163948

models/full/300ksteps/gPO_sBM_c01_d11_mPO1_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb4fd31d8e02f04553c8546dc11d0e4d8e82cdb3d2ab494770b29c70fceb6c5
+size 163948

models/full/300ksteps/gPO_sBM_c01_d11_mPO1_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2081f25e1cab73d311c063dce96ceb5c9d7c4856f4361ee65559269be5a2e91e
+size 163948

models/full/300ksteps/gWA_sBM_c01_d25_mWA0_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d311836b1c771a98f9fd5554d415a02c27670f9f558aa8acbc44de494f19211f
+size 163948

models/full/300ksteps/gWA_sBM_c01_d25_mWA0_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26808a402879ea1d7bc60da6e7d4bedaba7ef2d6d006c4a9891b99b3c3dafbab
+size 163948

models/full/300ksteps/gWA_sBM_c01_d26_mWA0_ch02_1.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e797bfa19442b8b57fa0e8c3b2ae3464b7e4fbe15c6c840bb59b7301f1ffa728
+size 163948

models/full/300ksteps/gWA_sBM_c01_d26_mWA0_ch02_2.wav

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:008337b09ab3236d5308c5fe453e59ea7ec20e9403159a71be01a0d234de0b27
+size 163948

models/full/300ksteps/metrics.txt

@@ -0,0 +1,6 @@
+frechet_audio_distance: 4.5603623
+beat_coverage_score: 0.5098538
+beat_hit_score: 0.5345641
+f1_score: 0.3856068
+tempo_difference: 20.6619472
+clap_score: 0.6812113

models/full/audioldm_original_medium_stretch_pretrained.yaml

@@ -0,0 +1,207 @@
+metadata_root: "./data/dataset/metadata/dataset_root.json"
+log_directory: "./log/latent_diffusion_controlnet_beatdance"
+project: "audioldm_controlnet"
+precision: "high"
+
+variables:
+  sampling_rate: &sampling_rate 16000 
+  mel_bins: &mel_bins 64
+  latent_embed_dim: &latent_embed_dim 8 # TODO might need to change
+  latent_t_size: &latent_t_size 128 # TODO might need to change
+  latent_f_size: &latent_f_size 16
+  in_channels: &unet_in_channels 8 # The input channel of the UNet model
+  model_channels: &unet_model_channels 192
+  optimize_ddpm_parameter: &optimize_ddpm_parameter true
+  optimize_gpt: &optimize_gpt true
+  warmup_steps: &warmup_steps 2000
+  default_unet_params: &default_unet_params
+    image_size: 64 
+    extra_film_condition_dim: 512 # If you use film as extra condition, set this parameter. For example if you have two conditioning vectors each have dimension 512, then this number would be 1024
+    # context_dim: 
+    # - 768
+    in_channels: *unet_in_channels
+    out_channels: *latent_embed_dim
+    model_channels: *unet_model_channels
+    attention_resolutions:
+    - 8
+    - 4
+    - 2
+    num_res_blocks: 2
+    channel_mult: 
+    - 1
+    - 2
+    - 3
+    - 5
+    num_head_channels: 32
+    use_spatial_transformer: true
+    transformer_depth: 1
+    extra_sa_layer: False
+
+data: 
+  train: ["aist"]
+  val: "aist"
+  test: "aist"
+  class_label_indices: ""
+  dataloader_add_ons: [] 
+
+step:
+  validation_every_n_epochs: 10
+  save_checkpoint_every_n_steps: 10000
+  # limit_val_batches: 2
+  max_steps: 1000000
+  save_top_k: 1
+
+preprocessing:
+  audio:
+    sampling_rate: *sampling_rate
+    max_wav_value: 32768.0
+    duration: 5.12
+  stft:
+    filter_length: 1024
+    hop_length: 160
+    win_length: 1024
+  mel:
+    n_mel_channels: *mel_bins
+    mel_fmin: 0
+    mel_fmax: 8000 
+  # added for dance-controlnet
+  strech_augmentation:
+    additional_strech_rate: 0.2
+    stretch_prob: 0.7
+  motion:
+    target_length: *latent_t_size
+    camera_height: 1080
+    camera_width: 1920
+    scale_range_train: [1, 3]
+    scale_range_test: [2, 2]
+    fps_keypoints: 60
+    beat_dim: 2
+
+augmentation:
+  mixup: 0.0
+
+model:
+  target: audioldm_train.modules.latent_diffusion.controlnet.ControlLDM
+  params: 
+    # Autoencoder
+    first_stage_config:
+      base_learning_rate: 8.0e-06
+      target: audioldm_train.modules.latent_encoder.autoencoder.AutoencoderKL
+      params: 
+        reload_from_ckpt: "data/checkpoints/vae_mel_16k_64bins.ckpt"
+        sampling_rate: *sampling_rate
+        batchsize: 8
+        monitor: val/rec_loss
+        image_key: fbank
+        subband: 1
+        embed_dim: *latent_embed_dim
+        time_shuffle: 1
+        lossconfig:
+          target: audioldm_train.losses.LPIPSWithDiscriminator
+          params:
+            disc_start: 50001
+            kl_weight: 1000.0
+            disc_weight: 0.5
+            disc_in_channels: 1
+        ddconfig: 
+          double_z: true
+          mel_bins: *mel_bins # The frequency bins of mel spectrogram
+          z_channels: 8
+          resolution: 256
+          downsample_time: false
+          in_channels: 1
+          out_ch: 1
+          ch: 128 
+          ch_mult:
+          - 1
+          - 2
+          - 4
+          num_res_blocks: 2
+          attn_resolutions: []
+          dropout: 0.0
+    # Other parameters
+    base_learning_rate: 1.0e-4
+    warmup_steps: *warmup_steps
+    optimize_ddpm_parameter: *optimize_ddpm_parameter
+    sampling_rate: *sampling_rate
+    batchsize: 8
+    linear_start: 0.0015
+    linear_end: 0.0195
+    num_timesteps_cond: 1
+    log_every_t: 200
+    timesteps: 1000
+    unconditional_prob_cfg: 0.1
+    parameterization: eps # [eps, x0, v]
+    first_stage_key: fbank
+    latent_t_size: *latent_t_size # TODO might need to change
+    latent_f_size: *latent_f_size
+    channels: *latent_embed_dim # TODO might need to change
+    monitor: val/loss_simple_ema
+    scale_by_std: true
+    unet_config:
+      target: audioldm_train.modules.latent_diffusion.controlnet.ControlledUnetModel
+      params:
+        <<: *default_unet_params
+    cond_stage_config:
+      film_clap_cond1:
+        cond_stage_key: text
+        conditioning_key: film
+        target: audioldm_train.conditional_models.CLAPAudioEmbeddingClassifierFreev2
+        params:
+          pretrained_path: data/checkpoints/clap_music_speech_audioset_epoch_15_esc_89.98.pt
+          sampling_rate: 16000
+          embed_mode: text # or text
+          amodel: HTSAT-base
+    # added for ControlNet
+    controlnet_stage_config:
+      dance_controlnet:
+        controlnet_stage_key: motion
+        target: audioldm_train.modules.latent_diffusion.dance_controlnet.DanceControlNetWrapper
+        params:
+          feature_encoder_config:
+            target: audioldm_train.modules.motion_encoder.encoder.BeatDanceEncoderWrapper
+            params:
+              motion_bert_config:
+                target: audioldm_train.modules.motion_encoder.MotionBERT.DSTformer.DSTformerWrapper
+                params:
+                  dim_in: 3
+                  dim_out: 3
+                  dim_feat: 512 # default value: intermediate representation
+                  dim_rep: &dim_rep 512 # default value
+                  depth: 5 # default value
+                  num_heads: 8 # default value
+                  mlp_ratio: 2 # default value
+                  maxlen: 243 # default value
+                  num_joints: &num_joints 17
+              motion_bert_pretrained_weights_path: data/checkpoints/latest_epoch.bin
+              feature_mapper_config:
+                target: audioldm_train.modules.motion_encoder.encoder.MotionBERT2BeatDance2AudioLDMEncoder
+                params:
+                  kpt_num_joints: *num_joints
+                  kpt_feat_dim: *dim_rep
+                  audio_channels: *unet_model_channels
+                  audio_freq: *latent_f_size
+                  beatdance_output_dim: &beatdance_output_dim 256
+                  beatdance_config:
+                    target: BeatDance.model.clip_transformer.DanceOnlyBeatDanceWrapper
+                    params:
+                      beatdance_config_path: audioldm_train/config/2025_11_23_dance_controlnet_beatdance/aist_seg10_L10.json
+                      kpt_num_joints: *num_joints
+                      kpt_feat_dim: *dim_rep
+                      beat_dim: 2
+                      beatdance_output_dim: *beatdance_output_dim
+                      num_frames: *latent_t_size
+                  beatdance_pretrained_weights_path: data/checkpoints/model_best.pth
+                  freeze_beatdance: false
+          controlnet_model_config:
+            target: audioldm_train.modules.latent_diffusion.controlnet.ControlNet
+            params:
+              <<: *default_unet_params
+    evaluation_params:
+      unconditional_guidance_scale: 3.5
+      ddim_sampling_steps: 200
+      n_candidates_per_samples: 3
+    evaluator_config:
+      target: audioldm_train.metrics.eval.ControlNetEvaluationHelper
+      params:
+        sampling_rate: *sampling_rate

models/full/checkpoints/checkpoint-global_step=299999.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5673a101b25cc2d3e3b218574dcedf2a0fc9a8263e4d7363bab0001f7d28b239
+size 8031577085

models/full/wandb/run-20251202_121332-lc8aneeb/files/conda-environment.yaml

@@ -0,0 +1,193 @@
+name: audioldm_train
+channels:
+  - defaults
+dependencies:
+  - _libgcc_mutex=0.1=main
+  - _openmp_mutex=5.1=1_gnu
+  - bzip2=1.0.8=h5eee18b_6
+  - ca-certificates=2025.11.4=h06a4308_0
+  - expat=2.7.3=h3385a95_0
+  - ld_impl_linux-64=2.44=h153f514_2
+  - libffi=3.4.4=h6a678d5_1
+  - libgcc=15.2.0=h69a1729_7
+  - libgcc-ng=15.2.0=h166f726_7
+  - libgomp=15.2.0=h4751f2c_7
+  - libnsl=2.0.0=h5eee18b_0
+  - libstdcxx=15.2.0=h39759b7_7
+  - libstdcxx-ng=15.2.0=hc03a8fd_7
+  - libuuid=1.41.5=h5eee18b_0
+  - libxcb=1.17.0=h9b100fa_0
+  - libzlib=1.3.1=hb25bd0a_0
+  - ncurses=6.5=h7934f7d_0
+  - openssl=3.0.18=hd6dcaed_0
+  - pip=25.2=pyhc872135_1
+  - pthread-stubs=0.3=h0ce48e5_1
+  - python=3.10.19=h6fa692b_0
+  - readline=8.3=hc2a1206_0
+  - sqlite=3.51.0=h2a70700_0
+  - tk=8.6.15=h54e0aa7_0
+  - xorg-libx11=1.8.12=h9b100fa_1
+  - xorg-libxau=1.0.12=h9b100fa_0
+  - xorg-libxdmcp=1.1.5=h9b100fa_0
+  - xorg-xorgproto=2024.1=h5eee18b_1
+  - xz=5.6.4=h5eee18b_1
+  - zlib=1.3.1=hb25bd0a_0
+  - pip:
+      - absl-py==2.0.0
+      - aiohttp==3.8.6
+      - aiosignal==1.3.1
+      - antlr4-python3-runtime==4.9.3
+      - anyio==4.11.0
+      - appdirs==1.4.4
+      - asttokens==2.4.1
+      - async-timeout==4.0.3
+      - attrs==23.1.0
+      - audioldm-eval==0.0.5
+      - audioldm-train==0.1.0
+      - audioread==3.0.1
+      - backports-tarfile==1.2.0
+      - braceexpand==0.1.7
+      - build==1.3.0
+      - cachecontrol==0.14.3
+      - certifi==2023.7.22
+      - cffi==1.16.0
+      - charset-normalizer==3.3.2
+      - cleo==2.1.0
+      - click==8.1.7
+      - contourpy==1.2.0
+      - crashtest==0.4.1
+      - cryptography==46.0.3
+      - cycler==0.12.1
+      - decorator==5.1.1
+      - distlib==0.4.0
+      - docker-pycreds==0.4.0
+      - dulwich==0.24.10
+      - einops==0.7.0
+      - exceptiongroup==1.1.3
+      - executing==2.0.1
+      - fastjsonschema==2.21.2
+      - filelock==3.13.1
+      - findpython==0.7.0
+      - fonttools==4.44.0
+      - frozenlist==1.4.0
+      - fsspec==2023.10.0
+      - ftfy==6.1.1
+      - gitdb==4.0.11
+      - gitpython==3.1.40
+      - h11==0.16.0
+      - h5py==3.10.0
+      - hear21passt==0.0.23
+      - httpcore==1.0.9
+      - httpx==0.28.1
+      - huggingface-hub==0.17.3
+      - idna==3.4
+      - imageio==2.31.5
+      - importlib-metadata==8.7.0
+      - installer==0.7.0
+      - ipdb==0.13.13
+      - ipython==8.17.2
+      - jaraco-classes==3.4.0
+      - jaraco-context==6.0.1
+      - jaraco-functools==4.3.0
+      - jedi==0.19.1
+      - jeepney==0.9.0
+      - joblib==1.3.2
+      - keyring==25.6.0
+      - kiwisolver==1.4.5
+      - kornia==0.7.0
+      - laion-clap==1.1.7
+      - lazy-loader==0.3
+      - librosa==0.9.2
+      - lightning-utilities==0.9.0
+      - llvmlite==0.41.1
+      - matplotlib==3.8.1
+      - matplotlib-inline==0.1.6
+      - more-itertools==10.8.0
+      - msgpack==1.1.2
+      - multidict==6.0.4
+      - networkx==3.2.1
+      - numba==0.58.1
+      - numpy==1.23.5
+      - nvidia-cublas-cu11==11.10.3.66
+      - nvidia-cuda-nvrtc-cu11==11.7.99
+      - nvidia-cuda-runtime-cu11==11.7.99
+      - nvidia-cudnn-cu11==8.5.0.96
+      - omegaconf==2.3.0
+      - packaging==23.2
+      - pandas==2.1.3
+      - parso==0.8.3
+      - pbs-installer==2025.10.31
+      - pexpect==4.8.0
+      - pillow==10.1.0
+      - pkginfo==1.12.1.2
+      - platformdirs==4.0.0
+      - poetry==2.2.1
+      - poetry-core==2.2.1
+      - pooch==1.8.0
+      - progressbar==2.5
+      - prompt-toolkit==3.0.41
+      - protobuf==4.25.0
+      - psutil==5.9.6
+      - ptyprocess==0.7.0
+      - pure-eval==0.2.2
+      - pycparser==2.21
+      - pygments==2.16.1
+      - pyparsing==3.1.1
+      - pyproject-hooks==1.2.0
+      - python-dateutil==2.8.2
+      - pytorch-lightning==2.1.1
+      - pytz==2023.3.post1
+      - pyyaml==6.0.1
+      - rapidfuzz==3.14.3
+      - regex==2023.10.3
+      - requests==2.31.0
+      - requests-toolbelt==1.0.0
+      - resampy==0.4.2
+      - ruamel-yaml==0.18.5
+      - ruamel-yaml-clib==0.2.8
+      - safetensors==0.4.0
+      - scikit-image==0.22.0
+      - scikit-learn==1.3.2
+      - scipy==1.9.3
+      - secretstorage==3.4.0
+      - sentry-sdk==1.35.0
+      - setproctitle==1.3.3
+      - setuptools==68.2.2
+      - shellingham==1.5.4
+      - six==1.16.0
+      - smmap==5.0.1
+      - sniffio==1.3.1
+      - soundfile==0.12.1
+      - ssr-eval==0.0.7
+      - stack-data==0.6.3
+      - taming-transformers-rom1504==0.0.6
+      - threadpoolctl==3.2.0
+      - tifffile==2023.9.26
+      - timm==0.4.12
+      - tokenizers==0.13.3
+      - tomli==2.0.1
+      - tomlkit==0.13.3
+      - torch==1.13.1
+      - torchaudio==0.13.1
+      - torchlibrosa==0.0.9
+      - torchmetrics==1.2.0
+      - torchvision==0.14.1
+      - tqdm==4.66.1
+      - traitlets==5.13.0
+      - transformers==4.30.2
+      - trove-classifiers==2025.9.11.17
+      - typing-extensions==4.8.0
+      - tzdata==2023.3
+      - ujson==5.11.0
+      - urllib3==2.1.0
+      - virtualenv==20.35.4
+      - wandb==0.16.0
+      - wave==0.0.2
+      - wcwidth==0.2.9
+      - webdataset==0.2.75
+      - wget==3.2
+      - wheel==0.41.3
+      - yarl==1.9.2
+      - zipp==3.23.0
+      - zstandard==0.25.0
+prefix: /home/rkimura/.conda/envs/audioldm_train

models/full/wandb/run-20251202_121332-lc8aneeb/files/config.yaml

@@ -0,0 +1,372 @@
+wandb_version: 1
+
+metadata_root:
+  desc: null
+  value: ./data/dataset/metadata/dataset_root.json
+log_directory:
+  desc: null
+  value: ./log/latent_diffusion_controlnet_beatdance
+project:
+  desc: null
+  value: audioldm_controlnet
+precision:
+  desc: null
+  value: high
+variables:
+  desc: null
+  value:
+    sampling_rate: 16000
+    mel_bins: 64
+    latent_embed_dim: 8
+    latent_t_size: 128
+    latent_f_size: 16
+    in_channels: 8
+    model_channels: 192
+    optimize_ddpm_parameter: true
+    optimize_gpt: true
+    warmup_steps: 2000
+    default_unet_params:
+      image_size: 64
+      extra_film_condition_dim: 512
+      in_channels: 8
+      out_channels: 8
+      model_channels: 192
+      attention_resolutions:
+      - 8
+      - 4
+      - 2
+      num_res_blocks: 2
+      channel_mult:
+      - 1
+      - 2
+      - 3
+      - 5
+      num_head_channels: 32
+      use_spatial_transformer: true
+      transformer_depth: 1
+      extra_sa_layer: false
+data:
+  desc: null
+  value:
+    train:
+    - aist
+    val: aist
+    test: aist
+    class_label_indices: ''
+    dataloader_add_ons: []
+step:
+  desc: null
+  value:
+    validation_every_n_epochs: 10
+    save_checkpoint_every_n_steps: 10000
+    max_steps: 1000000
+    save_top_k: 1
+preprocessing:
+  desc: null
+  value:
+    audio:
+      sampling_rate: 16000
+      max_wav_value: 32768.0
+      duration: 5.12
+    stft:
+      filter_length: 1024
+      hop_length: 160
+      win_length: 1024
+    mel:
+      n_mel_channels: 64
+      mel_fmin: 0
+      mel_fmax: 8000
+    strech_augmentation:
+      additional_strech_rate: 0.2
+      stretch_prob: 0.7
+    motion:
+      target_length: 128
+      camera_height: 1080
+      camera_width: 1920
+      scale_range_train:
+      - 1
+      - 3
+      scale_range_test:
+      - 2
+      - 2
+      fps_keypoints: 60
+      beat_dim: 2
+augmentation:
+  desc: null
+  value:
+    mixup: 0.0
+model:
+  desc: null
+  value:
+    target: audioldm_train.modules.latent_diffusion.controlnet.ControlLDM
+    params:
+      first_stage_config:
+        base_learning_rate: 8.0e-06
+        target: audioldm_train.modules.latent_encoder.autoencoder.AutoencoderKL
+        params:
+          reload_from_ckpt: data/checkpoints/vae_mel_16k_64bins.ckpt
+          sampling_rate: 16000
+          batchsize: 8
+          monitor: val/rec_loss
+          image_key: fbank
+          subband: 1
+          embed_dim: 8
+          time_shuffle: 1
+          lossconfig:
+            target: audioldm_train.losses.LPIPSWithDiscriminator
+            params:
+              disc_start: 50001
+              kl_weight: 1000.0
+              disc_weight: 0.5
+              disc_in_channels: 1
+          ddconfig:
+            double_z: true
+            mel_bins: 64
+            z_channels: 8
+            resolution: 256
+            downsample_time: false
+            in_channels: 1
+            out_ch: 1
+            ch: 128
+            ch_mult:
+            - 1
+            - 2
+            - 4
+            num_res_blocks: 2
+            attn_resolutions: []
+            dropout: 0.0
+      base_learning_rate: 0.0001
+      warmup_steps: 2000
+      optimize_ddpm_parameter: true
+      sampling_rate: 16000
+      batchsize: 8
+      linear_start: 0.0015
+      linear_end: 0.0195
+      num_timesteps_cond: 1
+      log_every_t: 200
+      timesteps: 1000
+      unconditional_prob_cfg: 0.1
+      parameterization: eps
+      first_stage_key: fbank
+      latent_t_size: 128
+      latent_f_size: 16
+      channels: 8
+      monitor: val/loss_simple_ema
+      scale_by_std: true
+      unet_config:
+        target: audioldm_train.modules.latent_diffusion.controlnet.ControlledUnetModel
+        params:
+          image_size: 64
+          extra_film_condition_dim: 512
+          in_channels: 8
+          out_channels: 8
+          model_channels: 192
+          attention_resolutions:
+          - 8
+          - 4
+          - 2
+          num_res_blocks: 2
+          channel_mult:
+          - 1
+          - 2
+          - 3
+          - 5
+          num_head_channels: 32
+          use_spatial_transformer: true
+          transformer_depth: 1
+          extra_sa_layer: false
+      cond_stage_config:
+        film_clap_cond1:
+          cond_stage_key: text
+          conditioning_key: film
+          target: audioldm_train.conditional_models.CLAPAudioEmbeddingClassifierFreev2
+          params:
+            pretrained_path: data/checkpoints/clap_music_speech_audioset_epoch_15_esc_89.98.pt
+            sampling_rate: 16000
+            embed_mode: text
+            amodel: HTSAT-base
+      controlnet_stage_config:
+        dance_controlnet:
+          controlnet_stage_key: motion
+          target: audioldm_train.modules.latent_diffusion.dance_controlnet.DanceControlNetWrapper
+          params:
+            feature_encoder_config:
+              target: audioldm_train.modules.motion_encoder.encoder.BeatDanceEncoderWrapper
+              params:
+                motion_bert_config:
+                  target: audioldm_train.modules.motion_encoder.MotionBERT.DSTformer.DSTformerWrapper
+                  params:
+                    dim_in: 3
+                    dim_out: 3
+                    dim_feat: 512
+                    dim_rep: 512
+                    depth: 5
+                    num_heads: 8
+                    mlp_ratio: 2
+                    maxlen: 243
+                    num_joints: 17
+                motion_bert_pretrained_weights_path: data/checkpoints/latest_epoch.bin
+                feature_mapper_config:
+                  target: audioldm_train.modules.motion_encoder.encoder.MotionBERT2BeatDance2AudioLDMEncoder
+                  params:
+                    kpt_num_joints: 17
+                    kpt_feat_dim: 512
+                    audio_channels: 192
+                    audio_freq: 16
+                    beatdance_output_dim: 256
+                    beatdance_config:
+                      target: BeatDance.model.clip_transformer.DanceOnlyBeatDanceWrapper
+                      params:
+                        beatdance_config_path: audioldm_train/config/2025_11_23_dance_controlnet_beatdance/aist_seg10_L10.json
+                        kpt_num_joints: 17
+                        kpt_feat_dim: 512
+                        beat_dim: 2
+                        beatdance_output_dim: 256
+                        num_frames: 128
+                    beatdance_pretrained_weights_path: data/checkpoints/model_best.pth
+                    freeze_beatdance: false
+            controlnet_model_config:
+              target: audioldm_train.modules.latent_diffusion.controlnet.ControlNet
+              params:
+                image_size: 64
+                extra_film_condition_dim: 512
+                in_channels: 8
+                out_channels: 8
+                model_channels: 192
+                attention_resolutions:
+                - 8
+                - 4
+                - 2
+                num_res_blocks: 2
+                channel_mult:
+                - 1
+                - 2
+                - 3
+                - 5
+                num_head_channels: 32
+                use_spatial_transformer: true
+                transformer_depth: 1
+                extra_sa_layer: false
+      evaluation_params:
+        unconditional_guidance_scale: 3.5
+        ddim_sampling_steps: 200
+        n_candidates_per_samples: 3
+      evaluator_config:
+        target: audioldm_train.metrics.eval.ControlNetEvaluationHelper
+        params:
+          sampling_rate: 16000
+reload_from_ckpt:
+  desc: null
+  value: data/checkpoints/audioldm-m-full.ckpt
+_wandb:
+  desc: null
+  value:
+    python_version: 3.10.19
+    cli_version: 0.16.0
+    framework: huggingface
+    huggingface_version: 4.30.2
+    is_jupyter_run: false
+    is_kaggle_kernel: false
+    start_time: 1764645212.043826
+    t:
+      1:
+      - 1
+      - 5
+      - 9
+      - 11
+      - 41
+      - 49
+      - 53
+      - 55
+      - 63
+      - 103
+      2:
+      - 1
+      - 5
+      - 9
+      - 11
+      - 41
+      - 49
+      - 53
+      - 55
+      - 63
+      - 103
+      3:
+      - 7
+      - 13
+      - 16
+      - 23
+      4: 3.10.19
+      5: 0.16.0
+      6: 4.30.2
+      8:
+      - 5
+      13: linux-x86_64
+    m:
+    - 1: trainer/global_step
+      6:
+      - 3
+    - 1: train/loss_simple_step
+      5: 1
+      6:
+      - 1
+    - 1: train/loss_vlb_step
+      5: 1
+      6:
+      - 1
+    - 1: train/loss_step
+      5: 1
+      6:
+      - 1
+    - 1: global_step
+      5: 1
+      6:
+      - 1
+    - 1: lr_abs
+      5: 1
+      6:
+      - 1
+    - 1: epoch
+      5: 1
+      6:
+      - 1
+    - 1: train/loss_simple_epoch
+      5: 1
+      6:
+      - 1
+    - 1: train/loss_vlb_epoch
+      5: 1
+      6:
+      - 1
+    - 1: train/loss_epoch
+      5: 1
+      6:
+      - 1
+    - 1: val/loss
+      5: 1
+      6:
+      - 1
+    - 1: val/frechet_audio_distance
+      5: 1
+      6:
+      - 1
+    - 1: val/beat_coverage_score
+      5: 1
+      6:
+      - 1
+    - 1: val/beat_hit_score
+      5: 1
+      6:
+      - 1
+    - 1: val/f1_score
+      5: 1
+      6:
+      - 1
+    - 1: val/tempo_difference
+      5: 1
+      6:
+      - 1
+    - 1: val/clap_score
+      5: 1
+      6:
+      - 1

models/full/wandb/run-20251202_121332-lc8aneeb/files/output.log

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a310a06109df3e2907acea804e43a7ee25ddf459462318b7ed99a199ce78480
+size 30423395

models/full/wandb/run-20251202_121332-lc8aneeb/files/requirements.txt

@@ -0,0 +1,158 @@
+absl-py==2.0.0
+aiohttp==3.8.6
+aiosignal==1.3.1
+antlr4-python3-runtime==4.9.3
+anyio==4.11.0
+appdirs==1.4.4
+asttokens==2.4.1
+async-timeout==4.0.3
+attrs==23.1.0
+audioldm-eval==0.0.5
+audioldm-train==0.1.0
+audioread==3.0.1
+backports.tarfile==1.2.0
+braceexpand==0.1.7
+build==1.3.0
+cachecontrol==0.14.3
+certifi==2023.7.22
+cffi==1.16.0
+charset-normalizer==3.3.2
+cleo==2.1.0
+click==8.1.7
+contourpy==1.2.0
+crashtest==0.4.1
+cryptography==46.0.3
+cycler==0.12.1
+decorator==5.1.1
+distlib==0.4.0
+docker-pycreds==0.4.0
+dulwich==0.24.10
+einops==0.7.0
+exceptiongroup==1.1.3
+executing==2.0.1
+fastjsonschema==2.21.2
+filelock==3.13.1
+findpython==0.7.0
+fonttools==4.44.0
+frozenlist==1.4.0
+fsspec==2023.10.0
+ftfy==6.1.1
+gitdb==4.0.11
+gitpython==3.1.40
+h11==0.16.0
+h5py==3.10.0
+hear21passt==0.0.23
+httpcore==1.0.9
+httpx==0.28.1
+huggingface-hub==0.17.3
+idna==3.4
+imageio==2.31.5
+importlib-metadata==8.7.0
+installer==0.7.0
+ipdb==0.13.13
+ipython==8.17.2
+jaraco-functools==4.3.0
+jaraco.classes==3.4.0
+jaraco.context==6.0.1
+jedi==0.19.1
+jeepney==0.9.0
+joblib==1.3.2
+keyring==25.6.0
+kiwisolver==1.4.5
+kornia==0.7.0
+laion-clap==1.1.7
+lazy-loader==0.3
+librosa==0.9.2
+lightning-utilities==0.9.0
+llvmlite==0.41.1
+matplotlib-inline==0.1.6
+matplotlib==3.8.1
+more-itertools==10.8.0
+msgpack==1.1.2
+multidict==6.0.4
+networkx==3.2.1
+numba==0.58.1
+numpy==1.23.5
+nvidia-cublas-cu11==11.10.3.66
+nvidia-cuda-nvrtc-cu11==11.7.99
+nvidia-cuda-runtime-cu11==11.7.99
+nvidia-cudnn-cu11==8.5.0.96
+omegaconf==2.3.0
+packaging==23.2
+pandas==2.1.3
+parso==0.8.3
+pbs-installer==2025.10.31
+pexpect==4.8.0
+pillow==10.1.0
+pip==25.2
+pkginfo==1.12.1.2
+platformdirs==4.0.0
+poetry-core==2.2.1
+poetry==2.2.1
+pooch==1.8.0
+progressbar==2.5
+prompt-toolkit==3.0.41
+protobuf==4.25.0
+psutil==5.9.6
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pycparser==2.21
+pygments==2.16.1
+pyparsing==3.1.1
+pyproject-hooks==1.2.0
+python-dateutil==2.8.2
+pytorch-lightning==2.1.1
+pytz==2023.3.post1
+pyyaml==6.0.1
+rapidfuzz==3.14.3
+regex==2023.10.3
+requests-toolbelt==1.0.0
+requests==2.31.0
+resampy==0.4.2
+ruamel.yaml.clib==0.2.8
+ruamel.yaml==0.18.5
+safetensors==0.4.0
+scikit-image==0.22.0
+scikit-learn==1.3.2
+scipy==1.9.3
+secretstorage==3.4.0
+sentry-sdk==1.35.0
+setproctitle==1.3.3
+setuptools==68.2.2
+shellingham==1.5.4
+six==1.16.0
+smmap==5.0.1
+sniffio==1.3.1
+soundfile==0.12.1
+ssr-eval==0.0.7
+stack-data==0.6.3
+taming-transformers-rom1504==0.0.6
+threadpoolctl==3.2.0
+tifffile==2023.9.26
+timm==0.4.12
+tokenizers==0.13.3
+tomli==2.0.1
+tomlkit==0.13.3
+torch==1.13.1
+torchaudio==0.13.1
+torchlibrosa==0.0.9
+torchmetrics==1.2.0
+torchvision==0.14.1
+tqdm==4.66.1
+traitlets==5.13.0
+transformers==4.30.2
+trove-classifiers==2025.9.11.17
+typing-extensions==4.8.0
+tzdata==2023.3
+ujson==5.11.0
+urllib3==2.1.0
+virtualenv==20.35.4
+wandb==0.16.0
+wave==0.0.2
+wcwidth==0.2.9
+webdataset==0.2.75
+wget==3.2
+wheel==0.41.3
+yarl==1.9.2
+zipp==3.23.0
+zstandard==0.25.0

models/full/wandb/run-20251202_121332-lc8aneeb/files/wandb-metadata.json

@@ -0,0 +1,541 @@
+{
+    "os": "Linux-6.8.0-85-generic-x86_64-with-glibc2.35",
+    "python": "3.10.19",
+    "heartbeatAt": "2025-12-02T03:13:33.101575",
+    "startedAt": "2025-12-02T03:13:32.036863",
+    "docker": null,
+    "cuda": null,
+    "args": [
+        "-c",
+        "audioldm_train/config/2025_11_23_dance_controlnet_beatdance/audioldm_original_medium_stretch_pretrained.yaml",
+        "--reload_from_ckpt",
+        "data/checkpoints/audioldm-m-full.ckpt"
+    ],
+    "state": "running",
+    "program": "/home/rkimura/ra/AudioLDM-ControlNet/audioldm_train/train/latent_diffusion_controlnet_beatdance.py",
+    "codePathLocal": "audioldm_train/train/latent_diffusion_controlnet_beatdance.py",
+    "codePath": "audioldm_train/train/latent_diffusion_controlnet_beatdance.py",
+    "git": {
+        "remote": "git@github.com:kmraven/AudioLDM-ControlNet.git",
+        "commit": "75ce2b58f91b028358342d44437676326dd1e0d5"
+    },
+    "email": "128337097+kmraven@users.noreply.github.com",
+    "root": "/home/rkimura/ra/AudioLDM-ControlNet",
+    "host": "v105",
+    "username": "rkimura",
+    "executable": "/home/rkimura/.conda/envs/audioldm_train/bin/python3",
+    "cpu_count": 48,
+    "cpu_count_logical": 96,
+    "cpu_freq": {
+        "current": 1558.8479583333335,
+        "min": 800.0,
+        "max": 3500.0
+    },
+    "cpu_freq_per_core": [
+        {
+            "current": 799.992,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.203,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.008,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.008,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 799.992,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 2300.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 799.992,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 799.984,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 2300.023,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 799.984,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 1500.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 799.992,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 2799.972,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 1399.957,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 1042.763,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.008,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 2800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 799.991,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 3000.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 899.982,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 799.991,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 1000.019,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 1000.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 2800.028,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 799.984,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.008,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.008,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 3500.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 3499.964,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 900.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 799.992,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 1700.017,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 3500.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 3500.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 799.992,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.039,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 2300.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.007,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.555,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 1100.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 1399.93,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 1001.87,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 1113.1,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 1100.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 2800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 1400.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 900.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 999.99,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 999.99,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 2799.971,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.008,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 799.976,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 3419.497,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 900.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 900.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        },
+        {
+            "current": 800.0,
+            "min": 800.0,
+            "max": 3500.0
+        }
+    ],
+    "disk": {
+        "/": {
+            "total": 1758.8579597473145,
+            "used": 1498.264316558838
+        }
+    },
+    "gpu": "NVIDIA A30",
+    "gpu_count": 3,
+    "gpu_devices": [
+        {
+            "name": "NVIDIA A30",
+            "memory_total": 25769803776
+        },
+        {
+            "name": "NVIDIA A100 80GB PCIe",
+            "memory_total": 85899345920
+        },
+        {
+            "name": "NVIDIA A100-PCIE-40GB",
+            "memory_total": 42949672960
+        }
+    ],
+    "memory": {
+        "total": 251.5155143737793
+    }
+}

models/full/wandb/run-20251202_121332-lc8aneeb/files/wandb-summary.json

@@ -0,0 +1 @@
+{"train/loss_simple_step": 0.07464810460805893, "train/loss_vlb_step": 0.0004365834756754339, "train/loss_step": 0.07464810460805893, "global_step": 319399.0, "lr_abs": 9.999999747378752e-05, "epoch": 931, "trainer/global_step": 319399, "_timestamp": 1764856374.819423, "_runtime": 211162.77559685707, "_step": 7411, "train/loss_simple_epoch": 0.10853035002946854, "train/loss_vlb_epoch": 0.0024787569418549538, "train/loss_epoch": 0.10853035002946854, "val/loss": 0.36418431997299194, "val/frechet_audio_distance": 4.125982761383057, "val/beat_coverage_score": 0.39719799160957336, "val/beat_hit_score": 0.5204594731330872, "val/f1_score": 0.3390026390552521, "val/tempo_difference": 24.163623809814453, "val/clap_score": 0.6715897917747498, "_wandb": {"runtime": 211181}}

models/full/wandb/run-20251202_121332-lc8aneeb/logs/debug-internal.log

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f3f3a4b5ff8b2962c845406394601bd45c8d6a6ec0f07d89cc1d83c55a2032a
+size 45717908

models/full/wandb/run-20251202_121332-lc8aneeb/logs/debug.log

@@ -0,0 +1,28 @@
+2025-12-02 12:13:32,039 INFO    MainThread:550702 [wandb_setup.py:_flush():76] Current SDK version is 0.16.0
+2025-12-02 12:13:32,039 INFO    MainThread:550702 [wandb_setup.py:_flush():76] Configure stats pid to 550702
+2025-12-02 12:13:32,039 INFO    MainThread:550702 [wandb_setup.py:_flush():76] Loading settings from /home/rkimura/.config/wandb/settings
+2025-12-02 12:13:32,039 INFO    MainThread:550702 [wandb_setup.py:_flush():76] Loading settings from /home/rkimura/ra/AudioLDM-ControlNet/wandb/settings
+2025-12-02 12:13:32,039 INFO    MainThread:550702 [wandb_setup.py:_flush():76] Loading settings from environment variables: {}
+2025-12-02 12:13:32,039 INFO    MainThread:550702 [wandb_setup.py:_flush():76] Applying setup settings: {'_disable_service': False}
+2025-12-02 12:13:32,039 INFO    MainThread:550702 [wandb_setup.py:_flush():76] Inferring run settings from compute environment: {'program_relpath': 'audioldm_train/train/latent_diffusion_controlnet_beatdance.py', 'program_abspath': '/home/rkimura/ra/AudioLDM-ControlNet/audioldm_train/train/latent_diffusion_controlnet_beatdance.py', 'program': '/home/rkimura/ra/AudioLDM-ControlNet/audioldm_train/train/latent_diffusion_controlnet_beatdance.py'}
+2025-12-02 12:13:32,039 INFO    MainThread:550702 [wandb_init.py:_log_setup():524] Logging user logs to ./log/latent_diffusion_controlnet_beatdance/2025_11_23_dance_controlnet_beatdance/audioldm_original_medium_stretch_pretrained/wandb/run-20251202_121332-lc8aneeb/logs/debug.log
+2025-12-02 12:13:32,040 INFO    MainThread:550702 [wandb_init.py:_log_setup():525] Logging internal logs to ./log/latent_diffusion_controlnet_beatdance/2025_11_23_dance_controlnet_beatdance/audioldm_original_medium_stretch_pretrained/wandb/run-20251202_121332-lc8aneeb/logs/debug-internal.log
+2025-12-02 12:13:32,040 INFO    MainThread:550702 [wandb_init.py:init():564] calling init triggers
+2025-12-02 12:13:32,040 INFO    MainThread:550702 [wandb_init.py:init():571] wandb.init called with sweep_config: {}
+config: {'metadata_root': './data/dataset/metadata/dataset_root.json', 'log_directory': './log/latent_diffusion_controlnet_beatdance', 'project': 'audioldm_controlnet', 'precision': 'high', 'variables': {'sampling_rate': 16000, 'mel_bins': 64, 'latent_embed_dim': 8, 'latent_t_size': 128, 'latent_f_size': 16, 'in_channels': 8, 'model_channels': 192, 'optimize_ddpm_parameter': True, 'optimize_gpt': True, 'warmup_steps': 2000, 'default_unet_params': {'image_size': 64, 'extra_film_condition_dim': 512, 'in_channels': 8, 'out_channels': 8, 'model_channels': 192, 'attention_resolutions': [8, 4, 2], 'num_res_blocks': 2, 'channel_mult': [1, 2, 3, 5], 'num_head_channels': 32, 'use_spatial_transformer': True, 'transformer_depth': 1, 'extra_sa_layer': False}}, 'data': {'train': ['aist'], 'val': 'aist', 'test': 'aist', 'class_label_indices': '', 'dataloader_add_ons': []}, 'step': {'validation_every_n_epochs': 10, 'save_checkpoint_every_n_steps': 10000, 'max_steps': 1000000, 'save_top_k': 1}, 'preprocessing': {'audio': {'sampling_rate': 16000, 'max_wav_value': 32768.0, 'duration': 5.12}, 'stft': {'filter_length': 1024, 'hop_length': 160, 'win_length': 1024}, 'mel': {'n_mel_channels': 64, 'mel_fmin': 0, 'mel_fmax': 8000}, 'strech_augmentation': {'additional_strech_rate': 0.2, 'stretch_prob': 0.7}, 'motion': {'target_length': 128, 'camera_height': 1080, 'camera_width': 1920, 'scale_range_train': [1, 3], 'scale_range_test': [2, 2], 'fps_keypoints': 60, 'beat_dim': 2}}, 'augmentation': {'mixup': 0.0}, 'model': {'target': 'audioldm_train.modules.latent_diffusion.controlnet.ControlLDM', 'params': {'first_stage_config': {'base_learning_rate': 8e-06, 'target': 'audioldm_train.modules.latent_encoder.autoencoder.AutoencoderKL', 'params': {'reload_from_ckpt': 'data/checkpoints/vae_mel_16k_64bins.ckpt', 'sampling_rate': 16000, 'batchsize': 8, 'monitor': 'val/rec_loss', 'image_key': 'fbank', 'subband': 1, 'embed_dim': 8, 'time_shuffle': 1, 'lossconfig': {'target': 'audioldm_train.losses.LPIPSWithDiscriminator', 'params': {'disc_start': 50001, 'kl_weight': 1000.0, 'disc_weight': 0.5, 'disc_in_channels': 1}}, 'ddconfig': {'double_z': True, 'mel_bins': 64, 'z_channels': 8, 'resolution': 256, 'downsample_time': False, 'in_channels': 1, 'out_ch': 1, 'ch': 128, 'ch_mult': [1, 2, 4], 'num_res_blocks': 2, 'attn_resolutions': [], 'dropout': 0.0}}}, 'base_learning_rate': 0.0001, 'warmup_steps': 2000, 'optimize_ddpm_parameter': True, 'sampling_rate': 16000, 'batchsize': 8, 'linear_start': 0.0015, 'linear_end': 0.0195, 'num_timesteps_cond': 1, 'log_every_t': 200, 'timesteps': 1000, 'unconditional_prob_cfg': 0.1, 'parameterization': 'eps', 'first_stage_key': 'fbank', 'latent_t_size': 128, 'latent_f_size': 16, 'channels': 8, 'monitor': 'val/loss_simple_ema', 'scale_by_std': True, 'unet_config': {'target': 'audioldm_train.modules.latent_diffusion.controlnet.ControlledUnetModel', 'params': {'image_size': 64, 'extra_film_condition_dim': 512, 'in_channels': 8, 'out_channels': 8, 'model_channels': 192, 'attention_resolutions': [8, 4, 2], 'num_res_blocks': 2, 'channel_mult': [1, 2, 3, 5], 'num_head_channels': 32, 'use_spatial_transformer': True, 'transformer_depth': 1, 'extra_sa_layer': False}}, 'cond_stage_config': {'film_clap_cond1': {'cond_stage_key': 'text', 'conditioning_key': 'film', 'target': 'audioldm_train.conditional_models.CLAPAudioEmbeddingClassifierFreev2', 'params': {'pretrained_path': 'data/checkpoints/clap_music_speech_audioset_epoch_15_esc_89.98.pt', 'sampling_rate': 16000, 'embed_mode': 'text', 'amodel': 'HTSAT-base'}}}, 'controlnet_stage_config': {'dance_controlnet': {'controlnet_stage_key': 'motion', 'target': 'audioldm_train.modules.latent_diffusion.dance_controlnet.DanceControlNetWrapper', 'params': {'feature_encoder_config': {'target': 'audioldm_train.modules.motion_encoder.encoder.BeatDanceEncoderWrapper', 'params': {'motion_bert_config': {'target': 'audioldm_train.modules.motion_encoder.MotionBERT.DSTformer.DSTformerWrapper', 'params': {'dim_in': 3, 'dim_out': 3, 'dim_feat': 512, 'dim_rep': 512, 'depth': 5, 'num_heads': 8, 'mlp_ratio': 2, 'maxlen': 243, 'num_joints': 17}}, 'motion_bert_pretrained_weights_path': 'data/checkpoints/latest_epoch.bin', 'feature_mapper_config': {'target': 'audioldm_train.modules.motion_encoder.encoder.MotionBERT2BeatDance2AudioLDMEncoder', 'params': {'kpt_num_joints': 17, 'kpt_feat_dim': 512, 'audio_channels': 192, 'audio_freq': 16, 'beatdance_output_dim': 256, 'beatdance_config': {'target': 'BeatDance.model.clip_transformer.DanceOnlyBeatDanceWrapper', 'params': {'beatdance_config_path': 'audioldm_train/config/2025_11_23_dance_controlnet_beatdance/aist_seg10_L10.json', 'kpt_num_joints': 17, 'kpt_feat_dim': 512, 'beat_dim': 2, 'beatdance_output_dim': 256, 'num_frames': 128}}, 'beatdance_pretrained_weights_path': 'data/checkpoints/model_best.pth', 'freeze_beatdance': False}}}}, 'controlnet_model_config': {'target': 'audioldm_train.modules.latent_diffusion.controlnet.ControlNet', 'params': {'image_size': 64, 'extra_film_condition_dim': 512, 'in_channels': 8, 'out_channels': 8, 'model_channels': 192, 'attention_resolutions': [8, 4, 2], 'num_res_blocks': 2, 'channel_mult': [1, 2, 3, 5], 'num_head_channels': 32, 'use_spatial_transformer': True, 'transformer_depth': 1, 'extra_sa_layer': False}}}}}, 'evaluation_params': {'unconditional_guidance_scale': 3.5, 'ddim_sampling_steps': 200, 'n_candidates_per_samples': 3}, 'evaluator_config': {'target': 'audioldm_train.metrics.eval.ControlNetEvaluationHelper', 'params': {'sampling_rate': 16000}}}}, 'reload_from_ckpt': 'data/checkpoints/audioldm-m-full.ckpt'}
+2025-12-02 12:13:32,040 INFO    MainThread:550702 [wandb_init.py:init():614] starting backend
+2025-12-02 12:13:32,040 INFO    MainThread:550702 [wandb_init.py:init():618] setting up manager
+2025-12-02 12:13:32,042 INFO    MainThread:550702 [backend.py:_multiprocessing_setup():105] multiprocessing start_methods=fork,spawn,forkserver, using: spawn
+2025-12-02 12:13:32,043 INFO    MainThread:550702 [wandb_init.py:init():624] backend started and connected
+2025-12-02 12:13:32,054 INFO    MainThread:550702 [wandb_init.py:init():716] updated telemetry
+2025-12-02 12:13:32,061 INFO    MainThread:550702 [wandb_init.py:init():749] communicating run to backend with 90.0 second timeout
+2025-12-02 12:13:32,857 INFO    MainThread:550702 [wandb_run.py:_on_init():2254] communicating current version
+2025-12-02 12:13:32,958 INFO    MainThread:550702 [wandb_run.py:_on_init():2263] got version response upgrade_message: "wandb version 0.23.0 is available!  To upgrade, please run:\n $ pip install wandb --upgrade"
+
+2025-12-02 12:13:32,958 INFO    MainThread:550702 [wandb_init.py:init():800] starting run threads in backend
+2025-12-02 12:13:35,595 INFO    MainThread:550702 [wandb_run.py:_console_start():2233] atexit reg
+2025-12-02 12:13:35,595 INFO    MainThread:550702 [wandb_run.py:_redirect():2088] redirect: wrap_raw
+2025-12-02 12:13:35,595 INFO    MainThread:550702 [wandb_run.py:_redirect():2153] Wrapping output streams.
+2025-12-02 12:13:35,595 INFO    MainThread:550702 [wandb_run.py:_redirect():2178] Redirects installed.
+2025-12-02 12:13:35,596 INFO    MainThread:550702 [wandb_init.py:init():841] run started, returning control to user process
+2025-12-04 22:53:25,958 WARNING MsgRouterThr:550702 [router.py:message_loop():77] message_loop has been closed

models/full/wandb/run-20251202_121332-lc8aneeb/run-lc8aneeb.wandb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff4460cf1d6d7a1bb6076f0ab4c216d40165533321a4e6c16615aad7b6a47f6
+size 215739494