You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+1Lines changed: 1 addition & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -28,6 +28,7 @@
28
28
In addition to the specific generation tasks, Amphion includes several **vocoders** and **evaluation metrics**. A vocoder is an important module for producing high-quality audio signals, while evaluation metrics are critical for ensuring consistent metrics in generation tasks. Moreover, Amphion is dedicated to advancing audio generation in real-world applications, such as building **large-scale datasets** for speech synthesis.
29
29
30
30
## 🚀 News
31
+
-**2024/08/22**: The **Emilia** dataset is now publicly available! Explore the most extensive and diverse speech generation dataset now at [OpenXLab](https://openxlab.org.cn/datasets/Amphion/Emilia)! 👑
31
32
-**2024/07/01**: Amphion now releases **Emilia**, the first open-source multilingual in-the-wild dataset for speech generation with over 101k hours of speech data, and the **Emilia-Pipe**, the first open-source preprocessing pipeline designed to transform in-the-wild speech data into high-quality training data with annotations for speech generation! [](https://arxiv.org/abs/2407.05361)[](https://huggingface.co/datasets/amphion/Emilia)[](https://emilia-dataset.github.io/Emilia-Demo-Page/)[](preprocessors/Emilia/README.md)
32
33
-**2024/06/17**: Amphion has a new release for its **VALL-E** model! It uses Llama as its underlying architecture and has better model performance, faster training speed, and more readable codes compared to our first version. [](egs/tts/VALLE_V2/README.md)
33
34
-**2024/03/12**: Amphion now support **NaturalSpeech3 FACodec** and release pretrained checkpoints. [](https://arxiv.org/abs/2403.03100)[](https://huggingface.co/amphion/naturalspeech3_facodec)[](https://huggingface.co/spaces/amphion/naturalspeech3_facodec)[](models/codec/ns3_codec/README.md)
-**2024/08/22**: The **Emilia** dataset is now publicly available! Explore the most extensive and diverse speech generation dataset now at [OpenXLab](https://openxlab.org.cn/datasets/Amphion/Emilia)! 👑
9
12
-**2024/07/08**: Our preprint [paper](https://arxiv.org/abs/2407.05361) is now available! 🔥🔥🔥
10
13
-**2024/07/03**: We welcome everyone to check our [homepage](https://emilia-dataset.github.io/Emilia-Demo-Page/) for our brief introduction for Emilia dataset and our demos!
11
14
-**2024/07/01**: We release of Emilia and Emilia-Pipe! We welcome everyone to explore it! 🎉🎉🎉
12
15
13
16
## About ⭐️
14
-
🎤**Emilia** is a comprehensive, multilingual dataset with the following features:
17
+
The**Emilia** is a comprehensive, multilingual dataset with the following features:
15
18
- containing over *101k* hours of speech data;
16
19
- covering six different languages: *English (En), Chinese (Zh), German (De), French (Fr), Japanese (Ja), and Korean (Ko)*;
17
20
- containing diverse speech data with *various speaking styles*;
@@ -20,15 +23,26 @@ Detailed description for the dataset could be found in our [paper](https://arxiv
20
23
21
24
🛠️ **Emilia-Pipe** is the first open-source preprocessing pipeline designed to transform raw, in-the-wild speech data into high-quality training data with annotations for speech generation. This pipeline can process one hour of raw audio into model-ready data in just a few minutes, requiring only the raw speech data.
22
25
23
-
*To use the Emilia dataset, you can download the raw audio files from our provided source URL list on [HuggingFace](https://huggingface.co/datasets/amphion/Emilia) and use our open-source [Emilia-Pipe](.) preprocessing pipeline to preprocess the raw data and rebuild the dataset.*
26
+
## Dataset Usage 🎤
27
+
The Emilia dataset is now publicly available at [OpenDataLab](https://opendatalab.com/Amphion/Emilia)!
28
+
29
+
To download the Emilia dataset, please follow these steps:
30
+
31
+
1. Fill out the [Application Form](https://speechteam.feishu.cn/share/base/form/shrcn7z8VODrVkOelbx0YUeJDOh) to receive the PASSWORD.
32
+
2. Visit the [OpenXLab dataset](https://openxlab.org.cn/datasets/Amphion/Emilia/tree/main/raw) and click the "Apply Download" button.
33
+
3. Enter the PASSWORD you received in step 1 into the "Detailed Purpose Description" input box and submit your download request. Applications will only be approved if the correct PASSWORD is provided. Once approved, you can enjoy using the dataset!
34
+
24
35
25
-
*Please note that Emilia doesn't own the copyright of the audios; the copyright remains with the original owners of the video or audio. Additionally, users can easily use Emilia-Pipe to preprocess their own raw speech data for custom needs.*
36
+
The Emilia dataset will be structured as follows:
26
37
27
-
By open-sourcing the Emilia-Pipe code, we aim to enable the speech community to collaborate on large-scale speech generation research.
38
+
-**Speech Data**: High-quality audio recordings in .mp3 format.
39
+
-**Transcriptions**: Corresponding text transcriptions for each audio file.
28
40
29
-
This following README will introduce the installation and usage guide of the Emilia-Pipe.
41
+
*Please note that Emilia does not own the copyright to the audio files; the copyright remains with the original owners of the videos or audio. Users are permitted to use this dataset only for non-commercial purposes under the CC BY-NC-4.0 license.*
30
42
31
-
## Pipeline Overview 👀
43
+
44
+
## Emilia-Pipe Overview 👀
45
+
If you wish to re-build Emilia, you may download the raw audio files from the [provided URL list](https://huggingface.co/datasets/amphion/Emilia) and use our open-source [Emilia-Pipe](https://github.com/open-mmlab/Amphion/tree/main/preprocessors/Emilia) preprocessing pipeline to preprocess the raw data. Additionally, users can easily use Emilia-Pipe to preprocess their own raw speech data for custom needs. By open-sourcing the Emilia-Pipe code, we aim to enable the speech community to collaborate on large-scale speech generation research.
32
46
33
47
The Emilia-Pipe includes the following major steps:
34
48
@@ -152,7 +166,7 @@ If you use the Emilia dataset or the Emilia-Pipe pipeline, please cite the follo
152
166
title={Emilia: An Extensive, Multilingual, and Diverse Speech Dataset for Large-Scale Speech Generation},
153
167
author={He, Haorui and Shang, Zengqiang and Wang, Chaoren and Li, Xuyuan and Gu, Yicheng and Hua, Hua and Liu, Liwei and Yang, Chen and Li, Jiaqi and Shi, Peiyang and Wang, Yuancheng and Chen, Kai and Zhang, Pengyuan and Wu, Zhizheng},
154
168
journal={arXiv},
155
-
volume={abs/2407.05361}
169
+
volume={abs/2407.05361},
156
170
year={2024}
157
171
}
158
172
```
@@ -161,7 +175,7 @@ If you use the Emilia dataset or the Emilia-Pipe pipeline, please cite the follo
161
175
title={Amphion: An Open-Source Audio, Music and Speech Generation Toolkit},
162
176
author={Zhang, Xueyao and Xue, Liumeng and Gu, Yicheng and Wang, Yuancheng and He, Haorui and Wang, Chaoren and Chen, Xi and Fang, Zihao and Chen, Haopeng and Zhang, Junan and Tang, Tze Ying and Zou, Lexiao and Wang, Mingxuan and Han, Jun and Chen, Kai and Li, Haizhou and Wu, Zhizheng},
0 commit comments