code refactor

.gitignore

@@ -1,14 +1,14 @@
 *.wav
-/AudCodec/test/**/
-!/AudCodec/test/sample1_16k.wav
-!/AudCodec/test/sample2_22k.wav
-!/AudCodec/test/sample3_48k.wav
-!/AudCodec/test/sample4_16k.wav
-!/AudCodec/test/sample5_16k.wav
-!/AudCodec/test/sample6_48k.wav
-!/AudCodec/test/sample7_16k.wav
-!/AudCodec/test/sample8_16k.wav
-!/AudCodec/test/sample9_48k.wav
-!/AudCodec/test/sample10_16k.wav
+/SoundCodec/test/**/
+!/SoundCodec/test/sample1_16k.wav
+!/SoundCodec/test/sample2_22k.wav
+!/SoundCodec/test/sample3_48k.wav
+!/SoundCodec/test/sample4_16k.wav
+!/SoundCodec/test/sample5_16k.wav
+!/SoundCodec/test/sample6_48k.wav
+!/SoundCodec/test/sample7_16k.wav
+!/SoundCodec/test/sample8_16k.wav
+!/SoundCodec/test/sample9_48k.wav
+!/SoundCodec/test/sample10_16k.wav
 
 __pycache__/

README.md

@@ -1,19 +1,17 @@
 # Codec-SUPERB: Audio Codec Speech Processing Universal Performance Benchmark
 
-![Overview](AudCodec/img/Overview.png)
+![Overview](SoundCodec/img/Overview.png)
 
 Codec-SUPERB is a comprehensive benchmark designed to evaluate audio codec models across a variety of speech tasks. Our
 goal is to facilitate community collaboration and accelerate advancements in the field of speech processing by
 preserving and enhancing speech information quality.
 
-
 ## Table of Contents
 
 - [Introduction](#introduction)
 - [Key Features](#key-features)
 - [Installation](#installation)
 - [Usage](#usage)
-- [Benchmarking](#benchmarking)
 - [Contribution](#contribution)
 - [License](#license)
 
@@ -26,17 +24,22 @@ in audio quality and processing efficiency.
 ## Key Features
 
 ### Out-of-the-Box Codec Interface
+
 Codec-SUPERB offers an intuitive, out-of-the-box codec interface that allows for easy integration and testing of various
 codec models, facilitating quick iterations and experiments.
 
 ### Multi-Perspective Leaderboard
-Codec-SUPERB's unique blend of multi-perspective evaluation and an online leaderboard drives innovation in audio codec research by providing a comprehensive assessment and fostering competitive transparency among developers.
+
+Codec-SUPERB's unique blend of multi-perspective evaluation and an online leaderboard drives innovation in audio codec
+research by providing a comprehensive assessment and fostering competitive transparency among developers.
 
 ### Standardized Environment
+
 We ensure a standardized testing environment to guarantee fair and consistent comparison across all models. This
 uniformity brings reliability to benchmark results, making them universally interpretable.
 
 ### Unified Datasets
+
 We provide a collection of unified datasets, curated to test a wide range of speech processing scenarios. This ensures
 that models are evaluated under diverse conditions, reflecting real-world applications.
 
@@ -50,13 +53,31 @@ pip install -r requirements.txt
 
 ## Usage
 
-Detailed instructions on how to use Codec-SUPERB, including preparing your codec model and executing benchmark tests,
-can be found in the `docs` directory.
+### [Leaderboard]()
+
+### Out of the Box Codec Interface
 
-## Benchmarking
+```python
+from SoundCodec import codec
+import torchaudio
 
-Codec-SUPERB supports a comprehensive suite of speech tasks, from speech recognition to audio quality assessment, each
-designed to rigorously evaluate the capabilities of audio codec models.
+# get all available codec
+print(codec.list_codec())
+# load codec by name, use encodec as example
+encodec_24k_6bps = codec.load_codec('encodec_24k_6bps')
+
+# load audio
+waveform, sample_rate = torchaudio.load('sample audio')
+resampled_waveform = waveform.numpy()[-1]
+data_item = {'audio': {'array': resampled_waveform,
+                       'sampling_rate': sample_rate}}
+
+# extract unit
+sound_unit = encodec_24k_6bps.extract_unit(data_item).unit
+
+# sound synthesis
+decoded_waveform = encodec_24k_6bps.synth(sound_unit, local_save=False)['audio']['array']
+```
 
 ## Contribution
 
@@ -67,7 +88,6 @@ enhancing the benchmarking framework. Please see `CONTRIBUTING.md` for more deta
 
 This project is licensed under the MIT License - see the `LICENSE` file for details.
 
-
 ## Reference Audio Codec Repositories：
 
 - https://github.com/ZhangXInFD/SpeechTokenizer

AudCodec/base_codec/academicodec.py → SoundCodec/base_codec/academicodec.py

@@ -12,7 +12,7 @@
 from torch.nn.utils import spectral_norm
 from torch.nn.utils import weight_norm
 from librosa.util import normalize
-from AudCodec.base_codec.general import save_audio, ExtractedUnit
+from SoundCodec.base_codec.general import save_audio, ExtractedUnit
 
 LRELU_SLOPE = 0.1
 

AudCodec/base_codec/audiodec.py → SoundCodec/base_codec/audiodec.py

@@ -1,6 +1,6 @@
 import nlp2
 import torch
-from AudCodec.base_codec.general import save_audio, ExtractedUnit
+from SoundCodec.base_codec.general import save_audio, ExtractedUnit
 
 
 class BaseCodec:

AudCodec/base_codec/descript_audio_codec.py → SoundCodec/base_codec/descript_audio_codec.py

@@ -1,4 +1,4 @@
-from AudCodec.base_codec.general import save_audio, ExtractedUnit
+from SoundCodec.base_codec.general import save_audio, ExtractedUnit
 import torch
 from audiotools import AudioSignal
 

AudCodec/base_codec/encodec.py → SoundCodec/base_codec/encodec.py

@@ -1,5 +1,5 @@
 import torch
-from AudCodec.base_codec.general import save_audio, ExtractedUnit
+from SoundCodec.base_codec.general import save_audio, ExtractedUnit
 
 
 class BaseCodec:

AudCodec/base_codec/encodec_hf.py → SoundCodec/base_codec/encodec_hf.py

@@ -1,6 +1,6 @@
 import torch
 from transformers import AutoModel, AutoProcessor
-from AudCodec.base_codec.general import save_audio, ExtractedUnit
+from SoundCodec.base_codec.general import save_audio, ExtractedUnit
 
 
 class BaseCodec:

AudCodec/base_codec/funcodec.py → SoundCodec/base_codec/funcodec.py

@@ -2,7 +2,7 @@
 import torch
 import os
 
-from AudCodec.base_codec.general import save_audio, ExtractedUnit
+from SoundCodec.base_codec.general import save_audio, ExtractedUnit
 from audiotools import AudioSignal
 
 

AudCodec/base_codec/speech_tokenizer.py → SoundCodec/base_codec/speech_tokenizer.py

@@ -1,6 +1,6 @@
 import numpy
 
-from AudCodec.base_codec.general import save_audio, ExtractedUnit
+from SoundCodec.base_codec.general import save_audio, ExtractedUnit
 import torchaudio
 import torch
 import nlp2

AudCodec/codec/__init__.py → SoundCodec/codec/__init__.py

@@ -2,7 +2,7 @@
 
 
 def load_codec(codec_name):
-    module = __import__(f"codec.{codec_name}", fromlist=[codec_name])
+    module = __import__(f"SoundCodec.codec.{codec_name}", fromlist=[codec_name])
     return module.Codec()
 
 

AudCodec/codec/academicodec_hifi_16k_320d.py → SoundCodec/codec/academicodec_hifi_16k_320d.py

@@ -1,6 +1,6 @@
 import json
 import nlp2
-from AudCodec.base_codec.academicodec import BaseCodec
+from SoundCodec.base_codec.academicodec import BaseCodec
 
 
 class Codec(BaseCodec):

AudCodec/codec/academicodec_hifi_16k_320d_large_uni.py → SoundCodec/codec/academicodec_hifi_16k_320d_large_uni.py

@@ -1,6 +1,6 @@
 import json
 import nlp2
-from AudCodec.base_codec.academicodec import BaseCodec
+from SoundCodec.base_codec.academicodec import BaseCodec
 
 
 class Codec(BaseCodec):

AudCodec/codec/academicodec_hifi_24k_320d.py → SoundCodec/codec/academicodec_hifi_24k_320d.py

@@ -1,6 +1,6 @@
 import json
 import nlp2
-from AudCodec.base_codec.academicodec import BaseCodec
+from SoundCodec.base_codec.academicodec import BaseCodec
 
 
 class Codec(BaseCodec):

AudCodec/codec/audiodec_24k_320d.py → SoundCodec/codec/audiodec_24k_320d.py

@@ -1,4 +1,4 @@
-from AudCodec.base_codec.audiodec import BaseCodec
+from SoundCodec.base_codec.audiodec import BaseCodec
 import nlp2
 
 

AudCodec/codec/dac_16k.py → SoundCodec/codec/dac_16k.py

@@ -1,4 +1,4 @@
-from AudCodec.base_codec.descript_audio_codec import BaseCodec
+from SoundCodec.base_codec.descript_audio_codec import BaseCodec
 
 
 class Codec(BaseCodec):

AudCodec/codec/dac_24k.py → SoundCodec/codec/dac_24k.py

@@ -1,4 +1,4 @@
-from AudCodec.base_codec.descript_audio_codec import BaseCodec
+from SoundCodec.base_codec.descript_audio_codec import BaseCodec
 
 
 class Codec(BaseCodec):

AudCodec/codec/dac_44k.py → SoundCodec/codec/dac_44k.py

@@ -1,4 +1,4 @@
-from AudCodec.base_codec.descript_audio_codec import BaseCodec
+from SoundCodec.base_codec.descript_audio_codec import BaseCodec
 
 
 class Codec(BaseCodec):

AudCodec/codec/encodec_24k_12bps.py → SoundCodec/codec/encodec_24k_12bps.py

@@ -1,4 +1,4 @@
-from AudCodec.base_codec.encodec import BaseCodec
+from SoundCodec.base_codec.encodec import BaseCodec
 
 class Codec(BaseCodec):
     def config(self):

AudCodec/codec/encodec_24k_1_5bps.py → SoundCodec/codec/encodec_24k_1_5bps.py

@@ -1,4 +1,4 @@
-from AudCodec.base_codec.encodec import BaseCodec
+from SoundCodec.base_codec.encodec import BaseCodec
 
 class Codec(BaseCodec):
     def config(self):

AudCodec/codec/encodec_24k_24bps.py → SoundCodec/codec/encodec_24k_24bps.py

@@ -1,4 +1,4 @@
-from AudCodec.base_codec.encodec import BaseCodec
+from SoundCodec.base_codec.encodec import BaseCodec
 
 class Codec(BaseCodec):
     def config(self):

AudCodec/codec/encodec_24k_3bps.py → SoundCodec/codec/encodec_24k_3bps.py

@@ -1,4 +1,4 @@
-from AudCodec.base_codec.encodec import BaseCodec
+from SoundCodec.base_codec.encodec import BaseCodec
 
 class Codec(BaseCodec):
     def config(self):

AudCodec/codec/encodec_24k_6bps.py → SoundCodec/codec/encodec_24k_6bps.py

@@ -1,4 +1,4 @@
-from AudCodec.base_codec.encodec import BaseCodec
+from SoundCodec.base_codec.encodec import BaseCodec
 
 class Codec(BaseCodec):
     def config(self):

AudCodec/codec/funcodec_en_libritts_16k_gr1nq32ds320.py → SoundCodec/codec/funcodec_en_libritts_16k_gr1nq32ds320.py

@@ -1,6 +1,6 @@
 import nlp2
 
-from AudCodec.base_codec.funcodec import BaseCodec
+from SoundCodec.base_codec.funcodec import BaseCodec
 
 
 class Codec(BaseCodec):

AudCodec/codec/funcodec_en_libritts_16k_gr8nq32ds320.py → SoundCodec/codec/funcodec_en_libritts_16k_gr8nq32ds320.py

@@ -1,6 +1,6 @@
 import nlp2
 
-from AudCodec.base_codec.funcodec import BaseCodec
+from SoundCodec.base_codec.funcodec import BaseCodec
 
 
 class Codec(BaseCodec):

AudCodec/codec/funcodec_en_libritts_16k_nq32ds320.py → SoundCodec/codec/funcodec_en_libritts_16k_nq32ds320.py

@@ -1,6 +1,6 @@
 import nlp2
 
-from AudCodec.base_codec.funcodec import BaseCodec
+from SoundCodec.base_codec.funcodec import BaseCodec
 
 
 class Codec(BaseCodec):

AudCodec/codec/funcodec_en_libritts_16k_nq32ds640.py → SoundCodec/codec/funcodec_en_libritts_16k_nq32ds640.py

@@ -1,6 +1,6 @@
 import nlp2
 
-from AudCodec.base_codec.funcodec import BaseCodec
+from SoundCodec.base_codec.funcodec import BaseCodec
 
 
 class Codec(BaseCodec):

AudCodec/codec/funcodec_zh_en_16k_nq32ds320.py → SoundCodec/codec/funcodec_zh_en_16k_nq32ds320.py

@@ -1,6 +1,6 @@
 import nlp2
 
-from AudCodec.base_codec.funcodec import BaseCodec
+from SoundCodec.base_codec.funcodec import BaseCodec
 
 
 class Codec(BaseCodec):

AudCodec/codec/funcodec_zh_en_16k_nq32ds640.py → SoundCodec/codec/funcodec_zh_en_16k_nq32ds640.py

@@ -1,6 +1,6 @@
 import nlp2
 
-from AudCodec.base_codec.funcodec import BaseCodec
+from SoundCodec.base_codec.funcodec import BaseCodec
 
 
 class Codec(BaseCodec):

AudCodec/codec/speech_tokenizer_16k.py → SoundCodec/codec/speech_tokenizer_16k.py

@@ -1,4 +1,4 @@
-from AudCodec.base_codec.speech_tokenizer import BaseCodec
+from SoundCodec.base_codec.speech_tokenizer import BaseCodec
 import nlp2
 
 class Codec(BaseCodec):

AudCodec/test/code_extract_unit.py → SoundCodec/test/code_extract_unit.py

@@ -1,7 +1,7 @@
 import torch
 import torchaudio
 
-from AudCodec.codec import list_codec, load_codec
+from SoundCodec.codec import list_codec, load_codec
 
 if __name__ == '__main__':
     for sample_file in ['sample1_16k.wav', 'sample2_22k.wav', 'sample3_48k.wav', 'sample4_16k.wav',

AudCodec/test/code_synth.py → SoundCodec/test/code_synth.py

@@ -1,6 +1,6 @@
 import torchaudio
 
-from AudCodec.codec import list_codec, load_codec
+from SoundCodec.codec import list_codec, load_codec
 
 if __name__ == '__main__':
     for sample_file in ['sample1_16k.wav', 'sample2_22k.wav', 'sample3_48k.wav', 'sample4_16k.wav',

AudCodec/test/synth_cli_check.py → SoundCodec/test/synth_cli_check.py

@@ -3,7 +3,7 @@
 import torch
 
 from benchmarking import compute_metrics
-from AudCodec.codec import load_codec
+from SoundCodec.codec import load_codec
 import torchaudio
 import numpy as np
 

benchmarking.py

@@ -9,7 +9,7 @@
 from datasets import load_dataset, load_from_disk
 from collections import defaultdict
 from audiotools import AudioSignal
-from AudCodec.base_codec.general import pad_arrays_to_match
+from SoundCodec.base_codec.general import pad_arrays_to_match
 from metrics import get_metrics
 import psutil
 from tqdm.contrib.concurrent import process_map

dataset_checker.py

@@ -2,7 +2,7 @@
 import itertools
 import numpy as np
 from datasets import load_dataset
-from AudCodec.codec import list_codec
+from SoundCodec.codec import list_codec
 
 
 def load_datasets(dataset_name, splits):

dataset_creator.py

@@ -1,8 +1,8 @@
 import argparse
 from datasets import DatasetDict, Audio, load_from_disk
-from AudCodec.codec import load_codec, list_codec
-from AudCodec.dataset import load_dataset
-from AudCodec.dataset.general import extract_unit
+from SoundCodec.codec import load_codec, list_codec
+from SoundCodec.dataset import load_dataset
+from SoundCodec.dataset.general import extract_unit
 
 
 def run_experiment(dataset_name):

dataset_updater.py

@@ -1,6 +1,6 @@
 import argparse
 from datasets import Audio, Dataset, Value, Sequence
-from AudCodec.codec import load_codec, list_codec
+from SoundCodec.codec import load_codec, list_codec
 from datasets import load_dataset
 
 

setup.py

@@ -1,7 +1,7 @@
 from setuptools import setup, find_packages
 
 setup(
-    name='AudCodec',
+    name='SoundCodec',
     version='1.0',
     packages=find_packages(),
     install_requires=[],