update amphion citation and link in dualcodec readme. remove dependency of descript-audio-codec which can cause dependency conflict

Author: jiaqili3

models/codec/dualcodec/README.md

@@ -5,8 +5,8 @@
 [![arXiv](https://img.shields.io/badge/arXiv-2505.13000-brightgreen.svg?style=flat-square)](http://arxiv.org/abs/2505.13000)
 [![githubio](https://img.shields.io/badge/GitHub.io-Demo_Page-blue?logo=Github&style=flat-square)](https://dualcodec.github.io/)
 [![PyPI](https://img.shields.io/pypi/v/dualcodec?color=blue&label=PyPI&logo=PyPI&style=flat-square)](https://pypi.org/project/dualcodec/)
-![GitHub](https://img.shields.io/badge/Github-Dev_Release-pink?logo=Github&style=flat-square)
-![Amphion](https://img.shields.io/badge/Amphion-Stable_Release-blue?style=flat-square)
+[![GitHub](https://img.shields.io/badge/Github-Dev_Release-pink?logo=Github&style=flat-square)](https://github.com/jiaqili3/dualcodec)
+[![Amphion](https://img.shields.io/badge/Amphion-Stable_Release-blue?style=flat-square)](https://github.com/open-mmlab/Amphion/blob/main/models/codec/dualcodec/README.md)
 [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1VvUhsDffLdY5TdNuaqlLnYzIoXhvI8MK#scrollTo=Lsos3BK4J-4E)
 
 ## About
@@ -125,11 +125,11 @@ This will launch an app that allows you to upload a wav file and get the output
 ## DualCodec-based TTS models
 Models available: 
 - DualCodec-VALLE: A super fast 12.5Hz VALL-E TTS model based on DualCodec.
-- DualCodec-Voicebox: A flow matching decoder for DualCodec 12.5Hz's semantic codes.
+- DualCodec-Voicebox: A flow matching decoder for DualCodec 12.5Hz's semantic codes. (this can be used as the second stage of tts). The component alone is not a TTS.
 
 To continue, first install other necessary components for training:
 ```bash
-pip install "dualcodec[train]"
+pip install "dualcodec[tts]"
 ```
 Alternatively, if you want to install from source,
 ```bash
@@ -170,7 +170,11 @@ pip install -U wandb protobuf transformers
 ```bash
 pip install "dualcodec[tts]"
 ```
-2. Clone this repository and `cd` to the project root folder (the folder that contains this readme).
+2. Clone this repository and `cd` to the project root folder (the folder that contains this readme):
+```bash
+git clone https://github.com/jiaqili3/DualCodec.git
+cd DualCodec
+```
 
 3. To run example training on example Emilia German data:
 ```bash
@@ -228,4 +232,20 @@ data.segment_speech.segment_length=24000
   booktitle = {Proceedings of Interspeech 2025},
   year      = {2025}
 }
+```
+If you use this with Amphion toolkit, please consider citing:
+```bibtex
+@article{amphion2,
+  title        = {Overview of the Amphion Toolkit (v0.2)},
+  author       = {Jiaqi Li and Xueyao Zhang and Yuancheng Wang and Haorui He and Chaoren Wang and Li Wang and Huan Liao and Junyi Ao and Zeyu Xie and Yiqiao Huang and Junan Zhang and Zhizheng Wu},
+  year         = {2025},
+  journal      = {arXiv preprint arXiv:2501.15442},
+}
+
+@inproceedings{amphion,
+    author={Xueyao Zhang and Liumeng Xue and Yicheng Gu and Yuancheng Wang and Jiaqi Li and Haorui He and Chaoren Wang and Ting Song and Xi Chen and Zihao Fang and Haopeng Chen and Junan Zhang and Tze Ying Tang and Lexiao Zou and Mingxuan Wang and Jun Han and Kai Chen and Haizhou Li and Zhizheng Wu},
+    title={Amphion: An Open-Source Audio, Music and Speech Generation Toolkit},
+    booktitle={{IEEE} Spoken Language Technology Workshop, {SLT} 2024},
+    year={2024}
+}
 ```

models/codec/dualcodec/dualcodec/model_codec/dac_layers.py

@@ -0,0 +1,33 @@
+import numpy as np
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from einops import rearrange
+from torch.nn.utils import weight_norm
+
+
+def WNConv1d(*args, **kwargs):
+    return weight_norm(nn.Conv1d(*args, **kwargs))
+
+
+def WNConvTranspose1d(*args, **kwargs):
+    return weight_norm(nn.ConvTranspose1d(*args, **kwargs))
+
+
+# Scripting this brings model speed up 1.4x
+@torch.jit.script
+def snake(x, alpha):
+    shape = x.shape
+    x = x.reshape(shape[0], shape[1], -1)
+    x = x + (alpha + 1e-9).reciprocal() * torch.sin(alpha * x).pow(2)
+    x = x.reshape(shape)
+    return x
+
+
+class Snake1d(nn.Module):
+    def __init__(self, channels):
+        super().__init__()
+        self.alpha = nn.Parameter(torch.ones(1, channels, 1))
+
+    def forward(self, x):
+        return snake(x, self.alpha)

models/codec/dualcodec/dualcodec/model_codec/dac_model.py

@@ -15,9 +15,9 @@
 from audiotools.ml import BaseModel
 from torch import nn
 
-from dac.nn.layers import Snake1d
-from dac.nn.layers import WNConv1d
-from dac.nn.layers import WNConvTranspose1d
+from .dac_layers import Snake1d
+from .dac_layers import WNConv1d
+from .dac_layers import WNConvTranspose1d
 from .dac_quantize import ResidualVectorQuantize
 from easydict import EasyDict as edict
 import torch.nn.functional as F

models/codec/dualcodec/dualcodec/model_codec/dac_quantize.py

@@ -17,7 +17,7 @@
     from torch.nn.utils import weight_norm
 except:
     from torch.nn.utils.parameterizations import weight_norm
-from dac.nn.layers import WNConv1d
+from .dac_layers import WNConv1d
 
 
 class VectorQuantize(nn.Module):

models/codec/dualcodec/dualcodec/model_codec/dualcodec_model.py

@@ -17,9 +17,9 @@
 from torch import nn
 
 # from .base import CodecMixin
-from dac.nn.layers import Snake1d
-from dac.nn.layers import WNConv1d
-from dac.nn.layers import WNConvTranspose1d
+from .dac_layers import Snake1d
+from .dac_layers import WNConv1d
+from .dac_layers import WNConvTranspose1d
 from .dac_quantize import ResidualVectorQuantize
 from easydict import EasyDict as edict
 import torch.nn.functional as F

models/codec/dualcodec/pyproject.toml

@@ -1,10 +1,10 @@
 [project]
 name = "dualcodec"
-version = "0.3.7"
+version = "0.4.0"
 description = "The DualCodec neural audio codec."
 dependencies = [
     "transformers>=4.30.0",
-    "descript-audio-codec",
+    "descript-audiotools>=0.7.2",
     "huggingface_hub[cli]",
     "easydict",
     "torch",

models/codec/dualcodec/setup.py

@@ -0,0 +1,19 @@
+from setuptools import setup
+
+setup(
+    name="dualcodec",
+    packages=["dualcodec"],
+    install_requires=[
+        "transformers>=4.30.0",
+        "descript-audiotools>=0.7.2",
+        "huggingface_hub[cli]",
+        "easydict",
+        "torch",
+        "torchaudio",
+        "hydra-core",
+        "einops",
+        "safetensors",
+        "cached_path",
+    ],
+    python_requires=">=3.9",
+)