mtg/maest 📝🖼️🔢❓ → 🖼️
About
MAEST is a family of Transformer models based on PASST and focused on music analysis applications. The MAEST models are also available for inference in the Essentia library and for inference and training in the official repository.

Example Output
Output

Performance Metrics
44.51s
Prediction Time
126.00s
Total Time
All Input Parameters
{ "url": "https://www.youtube.com/watch?v=LclGelDVnac", "top_n": 10, "output_format": "Visualization" }
Input Parameters
- url
- YouTube URL to process (overrides audio input)
- audio
- Audio file to process
- top_n
- Top n music styles to show
- output_format
- Output either a bar chart visualization or a JSON blob
Output Schema
Output
Example Execution Logs
[youtube] LclGelDVnac: Downloading webpage [youtube] LclGelDVnac: Downloading player 9d15588c [dashsegments] Total fragments: 1 [download] Destination: /tmp/tmpt564hijc/audio.webm [download] 0.0% of ~3.15MiB at 15.11KiB/s ETA 03:33 [download] 0.1% of ~3.15MiB at 45.22KiB/s ETA 01:11 [download] 0.2% of ~3.15MiB at 104.79KiB/s ETA 00:30 [download] 0.5% of ~3.15MiB at 223.18KiB/s ETA 00:14 [download] 1.0% of ~3.15MiB at 458.29KiB/s ETA 00:06 [download] 2.0% of ~3.15MiB at 915.05KiB/s ETA 00:03 [download] 3.9% of ~3.15MiB at 1.76MiB/s ETA 00:01 [download] 7.9% of ~3.15MiB at 3.44MiB/s ETA 00:00 [download] 15.8% of ~3.15MiB at 6.72MiB/s ETA 00:00 [download] 31.7% of ~3.15MiB at 13.07MiB/s ETA 00:00 [download] 63.5% of ~3.15MiB at 25.12MiB/s ETA 00:00 [download] 100.0% of ~3.15MiB at 11.44MiB/s ETA 00:00 [download] 100.0% of ~3.15MiB at 11.41MiB/s ETA 00:00 [download] 100% of 3.15MiB in 00:00 [ffmpeg] Destination: /tmp/tmpt564hijc/audio.wav Deleting original file /tmp/tmpt564hijc/audio.webm (pass -k to keep) loading audio... running the model... plotting... 2023-11-04 15:30:04.017105: I tensorflow/core/platform/profile_utils/cpu_utils.cc:114] CPU Frequency: 2199995000 Hz 2023-11-04 15:30:09.659050: W tensorflow/core/grappler/optimizers/loop_optimizer.cc:906] Skipping loop optimization for Merge node with control input: StatefulPartitionedCall/StatefulPartitionedCall/assert_equal_177/Assert/AssertGuard/branch_executed/_1327 2023-11-04 15:30:17.716207: W tensorflow/core/framework/cpu_allocator_impl.cc:80] Allocation of 136282800 exceeds 10% of free system memory. 2023-11-04 15:30:18.018761: W tensorflow/core/framework/cpu_allocator_impl.cc:80] Allocation of 136282800 exceeds 10% of free system memory. 2023-11-04 15:30:18.320289: W tensorflow/core/framework/cpu_allocator_impl.cc:80] Allocation of 136282800 exceeds 10% of free system memory. 2023-11-04 15:30:18.605200: W tensorflow/core/framework/cpu_allocator_impl.cc:80] Allocation of 136282800 exceeds 10% of free system memory. 2023-11-04 15:30:18.891654: W tensorflow/core/framework/cpu_allocator_impl.cc:80] Allocation of 136282800 exceeds 10% of free system memory. 2023-11-04 15:30:38.754365: I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:937] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero 2023-11-04 15:30:38.756447: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1733] Found device 0 with properties: pciBusID: 0000:00:05.0 name: Tesla T4 computeCapability: 7.5 coreClock: 1.59GHz coreCount: 40 deviceMemorySize: 14.58GiB deviceMemoryBandwidth: 298.08GiB/s 2023-11-04 15:30:38.756486: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1766] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform. Skipping registering GPU devices... 2023-11-04 15:30:38.756508: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1258] Device interconnect StreamExecutor with strength 1 edge matrix: 2023-11-04 15:30:38.756517: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1264] 0 2023-11-04 15:30:38.756545: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1277] 0: N /usr/local/lib/python3.10/site-packages/seaborn/_core.py:1225: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead if pd.api.types.is_categorical_dtype(vector): /usr/local/lib/python3.10/site-packages/seaborn/_core.py:1225: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead if pd.api.types.is_categorical_dtype(vector): /usr/local/lib/python3.10/site-packages/seaborn/_core.py:1225: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead if pd.api.types.is_categorical_dtype(vector): done!
Version Details
- Version ID
170cfd0b56fb97ed732c815431e52546efac47b8a2b0096d58dd40b099191e01
- Version Created
- November 4, 2023