dathudeptrai commited on
Commit
b1d1fb5
1 Parent(s): 93aaac2

🦋 Update README

Browse files
Files changed (1) hide show
  1. README.md +70 -0
README.md ADDED
@@ -0,0 +1,70 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - tensorflowtts
4
+ - audio
5
+ - text-to-speech
6
+ - text-to-mel
7
+ language: chinese
8
+ license: apache-2.0
9
+ datasets:
10
+ - Baker
11
+ widget:
12
+ - text: "这是一个开源的端到端中文语音合成系统"
13
+ ---
14
+
15
+ # FastSpeech2 trained on KSS (Korean)
16
+ This repository provides a pretrained [FastSpeech2](https://arxiv.org/abs/2006.04558) trained on Baker dataset (Ch). For a detail of the model, we encourage you to read more about
17
+ [TensorFlowTTS](https://github.com/TensorSpeech/TensorFlowTTS).
18
+
19
+
20
+ ## Install TensorFlowTTS
21
+ First of all, please install TensorFlowTTS with the following command:
22
+ ```
23
+ pip install TensorFlowTTS
24
+ ```
25
+
26
+ ### Converting your Text to Mel Spectrogram
27
+ ```python
28
+ from tensorflow_tts.inference import AutoProcessor
29
+ from tensorflow_tts.inference import TFAutoModel
30
+
31
+ processor = AutoProcessor.from_pretrained("tensorspeech/tts-fastspeech2-baker-ch")
32
+ fastspeech2 = TFAutoModel.from_pretrained("tensorspeech/tts-fastspeech2-baker-ch")
33
+
34
+ text = "这是一个开源的端到端中文语音合成系统"
35
+
36
+ input_ids = processor.text_to_sequence(text)
37
+
38
+ mel_before, mel_after, duration_outputs, _, _ = fastspeech2.inference(
39
+ input_ids=tf.expand_dims(tf.convert_to_tensor(input_ids, dtype=tf.int32), 0),
40
+ speaker_ids=tf.convert_to_tensor([0], dtype=tf.int32),
41
+ speed_ratios=tf.convert_to_tensor([1.0], dtype=tf.float32),
42
+ f0_ratios =tf.convert_to_tensor([1.0], dtype=tf.float32),
43
+ energy_ratios =tf.convert_to_tensor([1.0], dtype=tf.float32),
44
+ )
45
+ ```
46
+
47
+ #### Referencing FastSpeech
48
+ ```
49
+ @misc{ren2021fastspeech,
50
+ title={FastSpeech 2: Fast and High-Quality End-to-End Text to Speech},
51
+ author={Yi Ren and Chenxu Hu and Xu Tan and Tao Qin and Sheng Zhao and Zhou Zhao and Tie-Yan Liu},
52
+ year={2021},
53
+ eprint={2006.04558},
54
+ archivePrefix={arXiv},
55
+ primaryClass={eess.AS}
56
+ }
57
+ ```
58
+
59
+ #### Referencing TensorFlowTTS
60
+ ```
61
+ @misc{TFTTS,
62
+ author = {Minh Nguyen, Alejandro Miguel Velasquez, Erogol, Kuan Chen, Dawid Kobus, Takuya Ebata,
63
+ Trinh Le and Yunchao He},
64
+ title = {TensorflowTTS},
65
+ year = {2020},
66
+ publisher = {GitHub},
67
+ journal = {GitHub repository},
68
+ howpublished = {\\url{https://github.com/TensorSpeech/TensorFlowTTS}},
69
+ }
70
+ ```