DeePAQ
DeePAQ uses pre-trained MERT to extract embeddings of size 256. The provided training_mapping.py maps embeddings to a MUSHRA-like scale (0–100).
Table of Contents
Installation
DeePAQ is built and tested on PyTorch 2.5.1, TorchVision 0.20.1, TorchAudio 2.5.1 and CUDA 12.1 runtime It can be either installed with pip or git.
pip
Checkpoints are not part of the PyPI package. Download the DeePAQ checkpoints, and the neural mapping checkpoint if you use mapping: nn, and point model_path / mapping_model_path at those files.
pip install DeePAQ
From a local build of this repository:
pip install dist/deepaq-0.1.0-py3-none-any.whl
git
git clone https://git.audiolabs.uni-erlangen.de/guanxin.jiang/audio-quality-assessment-dnn.git
cd audio-quality-assessment-dnn
git checkout DeePAQ
conda env create -f environment.yml
conda activate DeePAQ-env
Dataset
For evaluation the project requires signals under test, matched reference signals, and corresponding subjective scores in CSV format. Each CSV should include columns:
filepath_deg— path to the degraded/test signalfilepath_ref— (optional) path to the matched reference signalSG— (optional) subjective rating. If SG column exists in your csv file, then the script will automatically detect it and then calculate the overall Spearman and Pearson correlation between the mapped results and subjective ratings
Place your dataset files in the data/ folder.
Usage
Training
Run the main script with your training config:
python main.py --config_file src/config/train1_1.yaml
Evaluation
Extract Embeddings
If you pip install deepaq
import deepaq
wav_path='/path/test.wav'
checkpoint='/path/best_model.pt'
embs = deepaq.compute_embedding(wav_path, checkpoint, model_type='MERT', mapping_type='polynomial')
Full Reference
python main.py --config_file src/config/fr_eval.yaml
or if you pip install deepaq
deepaq --config_file src/config/fr_eval.yaml
In fr_eval.yaml config file
model— foundation modelmodel_path— checkpoint has been provided in out-models folder. For full reference, 2 checkpoints are provided, which are MERT-FR-2f and MERT-FR-bestmapping- choose the mapping functions: polynomial uses 3rd order polynomial mapping; spline uses quadratic B-spline (degree 2, order 3) with three internal knots; nn uses a neural network trained to map Euclidean distance to MUSHRA scale.mapping_model_path: ./out-models/Dist2SG_Mapping/best_model.pt (This is optional if polynomial or spline is used for mapping)test_files_csv— csv file containing the data for testingtest_root_wav— folder where your test data storedemb_out_dir- folder where you want to save your evalution resultsemb_out_file— csv file saves the evaluation resultsplot_out_file— png file saves scatterplot of the evaluation results
Non-matching Reference
python main.py --config_file src/config/nmr_eval.yaml
In nmr_eval.yaml config file
model— foundation modelmodel_path— checkpoint has been provided in out-models folder.mapping- choose the mapping functions: polynomial uses 3rd order polynomial mapping; spline uses quadratic B-spline (degree 2, order 3) with three internal knots; nn uses a neural network trained to map Euclidean distance to MUSHRA scale.mapping_model_path: ./out-models/Dist2SG_Mapping/best_model.pt (This is optional if polynomial or spline is used for mapping)test_files_csv— csv file containing the data for testingtest_root_wav— folder where your test data storedemb_out_dir- folder where you want to save your evalution resultsemb_out_file— csv file saves the evaluation resultsplot_out_file— png file saves scatterplot of the evaluation resultsnon_matching_Mref_root— folder where contains the non-matching reference with music contentnon_matching_Sref_root— folder where contains the non-matching reference with speech content
Notation
model wav2vec is for development. If users want to use DeePAQ for inference, wav2vec could be skipped; otherwise need to install fairseq for wav2vec
Metadata
Release files for DeePAQ 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| deepaq-0.1.0.tar.gz | 11.9 kB | Without provenance | Details for deepaq-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| deepaq-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for deepaq-0.1.0-py3-none-any.whl |
Total release size: 25.2 kB
Release files / deepaq-0.1.0.tar.gz
| Download URL | deepaq-0.1.0.tar.gz |
|---|---|
| Size | 11.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
7d6e4ae2c178d685e0f3ad232befd5dcf4d8ea0a0cc782112e7a8b5c874df637
|
|
BLAKE2b-256 checksum How to use checksums |
bb0a77d3ed2f3541115768271094bb78dc07245c8326b83c4a76000b000e3399
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.10.19
|
Release files / deepaq-0.1.0-py3-none-any.whl
| Download URL | deepaq-0.1.0-py3-none-any.whl |
|---|---|
| Size | 13.4 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
e8b7329eef7a72bf946c02265a63ed4ef35e3f60ba3169e9959ace47d71a3bdd
|
|
BLAKE2b-256 checksum How to use checksums |
a70887e4fb4fea5044a920470bb4c2e7df0719b4c27b00a20bd8d5b86d5853d8
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.10.19
|
Security for DeePAQ 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.