Spaces:
Running
on
Zero
Running
on
Zero
Commit
•
19d70cb
1
Parent(s):
4300fed
Update
Browse files
README.md
CHANGED
@@ -1,162 +1,8 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
| Language | Example |
|
10 |
-
| --- | --- |
|
11 |
-
| English | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-Default/speed_1.0/sent_000.wav) |
|
12 |
-
| English (American) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-US/speed_1.0/sent_000.wav) |
|
13 |
-
| English (British) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-BR/speed_1.0/sent_000.wav) |
|
14 |
-
| English (Indian) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN_INDIA/speed_1.0/sent_000.wav) |
|
15 |
-
| English (Australian) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/en/EN-AU/speed_1.0/sent_000.wav) |
|
16 |
-
| Spanish | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/es/ES/speed_1.0/sent_000.wav) |
|
17 |
-
| French | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/fr/FR/speed_1.0/sent_000.wav) |
|
18 |
-
| Chinese (mix EN) | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/zh/ZH/speed_1.0/sent_008.wav) |
|
19 |
-
| Japanese | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/jp/JP/speed_1.0/sent_000.wav) |
|
20 |
-
| Korean | [Link](https://myshell-public-repo-hosting.s3.amazonaws.com/myshellttsbase/examples/kr/KR/speed_1.0/sent_000.wav) |
|
21 |
-
|
22 |
-
Some other features include:
|
23 |
-
- The Chinese speaker supports `mixed Chinese and English`.
|
24 |
-
- Fast enough for `CPU real-time inference`.
|
25 |
-
|
26 |
-
## Install on Linux
|
27 |
-
```bash
|
28 |
-
git clone git@github.com:myshell-ai/MeloTTS.git
|
29 |
-
cd MeloTTS
|
30 |
-
pip install -e .
|
31 |
-
python -m unidic download
|
32 |
-
```
|
33 |
-
We welcome the open-source community to make this repo `Mac` and `Windows` compatible. If you find this repo useful, please consider contributing to the repo.
|
34 |
-
|
35 |
-
## Usage
|
36 |
-
|
37 |
-
### English with Multi Accents
|
38 |
-
```python
|
39 |
-
from melo.api import TTS
|
40 |
-
|
41 |
-
# Speed is adjustable
|
42 |
-
speed = 1.0
|
43 |
-
|
44 |
-
# CPU is sufficient for real-time inference.
|
45 |
-
# You can also change to cuda:0
|
46 |
-
device = 'cpu'
|
47 |
-
|
48 |
-
# English
|
49 |
-
text = "Did you ever hear a folk tale about a giant turtle?"
|
50 |
-
model = TTS(language='EN', device=device)
|
51 |
-
speaker_ids = model.hps.data.spk2id
|
52 |
-
|
53 |
-
# Default accent
|
54 |
-
output_path = 'en-default.wav'
|
55 |
-
model.tts_to_file(text, speaker_ids['EN-Default'], output_path, speed=speed)
|
56 |
-
|
57 |
-
# American accent
|
58 |
-
output_path = 'en-us.wav'
|
59 |
-
model.tts_to_file(text, speaker_ids['EN-US'], output_path, speed=speed)
|
60 |
-
|
61 |
-
# British accent
|
62 |
-
output_path = 'en-br.wav'
|
63 |
-
model.tts_to_file(text, speaker_ids['EN-BR'], output_path, speed=speed)
|
64 |
-
|
65 |
-
# Indian accent
|
66 |
-
output_path = 'en-india.wav'
|
67 |
-
model.tts_to_file(text, speaker_ids['EN_INDIA'], output_path, speed=speed)
|
68 |
-
|
69 |
-
# Australian accent
|
70 |
-
output_path = 'en-au.wav'
|
71 |
-
model.tts_to_file(text, speaker_ids['EN-AU'], output_path, speed=speed)
|
72 |
-
|
73 |
-
```
|
74 |
-
|
75 |
-
### Spanish
|
76 |
-
```python
|
77 |
-
from melo.api import TTS
|
78 |
-
|
79 |
-
# Speed is adjustable
|
80 |
-
speed = 1.0
|
81 |
-
|
82 |
-
# CPU is sufficient for real-time inference.
|
83 |
-
# You can also change to cuda:0
|
84 |
-
device = 'cpu'
|
85 |
-
|
86 |
-
text = "El resplandor del sol acaricia las olas, pintando el cielo con una paleta deslumbrante."
|
87 |
-
model = TTS(language='ES', device=device)
|
88 |
-
speaker_ids = model.hps.data.spk2id
|
89 |
-
|
90 |
-
output_path = 'es.wav'
|
91 |
-
model.tts_to_file(text, speaker_ids['ES'], output_path, speed=speed)
|
92 |
-
```
|
93 |
-
|
94 |
-
### French
|
95 |
-
```python
|
96 |
-
from melo.api import TTS
|
97 |
-
|
98 |
-
# Speed is adjustable
|
99 |
-
speed = 1.0
|
100 |
-
device = 'cpu' # or cuda:0
|
101 |
-
|
102 |
-
text = "La lueur dorée du soleil caresse les vagues, peignant le ciel d'une palette éblouissante."
|
103 |
-
model = TTS(language='FR', device=device)
|
104 |
-
speaker_ids = model.hps.data.spk2id
|
105 |
-
|
106 |
-
output_path = 'fr.wav'
|
107 |
-
model.tts_to_file(text, speaker_ids['FR'], output_path, speed=speed)
|
108 |
-
```
|
109 |
-
|
110 |
-
### Chinese
|
111 |
-
```python
|
112 |
-
from melo.api import TTS
|
113 |
-
|
114 |
-
# Speed is adjustable
|
115 |
-
speed = 1.0
|
116 |
-
device = 'cpu' # or cuda:0
|
117 |
-
|
118 |
-
text = "我最近在学习machine learning,希望能够在未来的artificial intelligence领域有所建树。"
|
119 |
-
model = TTS(language='ZH', device=device)
|
120 |
-
speaker_ids = model.hps.data.spk2id
|
121 |
-
|
122 |
-
output_path = 'zh.wav'
|
123 |
-
model.tts_to_file(text, speaker_ids['ZH'], output_path, speed=speed)
|
124 |
-
```
|
125 |
-
|
126 |
-
### Japanese
|
127 |
-
```python
|
128 |
-
from melo.api import TTS
|
129 |
-
|
130 |
-
# Speed is adjustable
|
131 |
-
speed = 1.0
|
132 |
-
device = 'cpu' # or cuda:0
|
133 |
-
|
134 |
-
text = "彼は毎朝ジョギングをして体を健康に保っています。"
|
135 |
-
model = TTS(language='JP', device=device)
|
136 |
-
speaker_ids = model.hps.data.spk2id
|
137 |
-
|
138 |
-
output_path = 'jp.wav'
|
139 |
-
model.tts_to_file(text, speaker_ids['JP'], output_path, speed=speed)
|
140 |
-
```
|
141 |
-
|
142 |
-
### Korean
|
143 |
-
```python
|
144 |
-
from melo.api import TTS
|
145 |
-
|
146 |
-
# Speed is adjustable
|
147 |
-
speed = 1.0
|
148 |
-
device = 'cpu' # or cuda:0
|
149 |
-
|
150 |
-
text = "안녕하세요! 오늘은 날씨가 정말 좋네요."
|
151 |
-
model = TTS(language='KR', device=device)
|
152 |
-
speaker_ids = model.hps.data.spk2id
|
153 |
-
|
154 |
-
output_path = 'kr.wav'
|
155 |
-
model.tts_to_file(text, speaker_ids['KR'], output_path, speed=speed)
|
156 |
-
```
|
157 |
-
|
158 |
-
## License
|
159 |
-
This library is under MIT License. Free for both commercial and non-commercial use.
|
160 |
-
|
161 |
-
## Acknowledgement
|
162 |
-
This implementation is based on several excellent projects, [TTS](https://github.com/coqui-ai/TTS), [VITS](https://github.com/jaywalnut310/vits), [VITS2](https://github.com/daniilrobnikov/vits2) and [Bert-VITS2](https://github.com/fishaudio/Bert-VITS2). We appreciate their awesome work!
|
|
|
1 |
+
---
|
2 |
+
title: MeloTTS
|
3 |
+
colorFrom: blue
|
4 |
+
colorTo: blue
|
5 |
+
sdk: gradio
|
6 |
+
app_file: app.py
|
7 |
+
pinned: false
|
8 |
+
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|