davidmezzetti commited on
Commit
d51b59a
1 Parent(s): db21534

Add model files

Browse files
Files changed (3) hide show
  1. README.md +30 -0
  2. config.yaml +92 -0
  3. model.onnx +3 -0
README.md CHANGED
@@ -1,3 +1,33 @@
1
  ---
 
 
 
 
 
 
 
 
2
  license: apache-2.0
3
  ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ tags:
3
+ - audio
4
+ - text-to-speech
5
+ - onnx
6
+ inference: false
7
+ language: en
8
+ datasets:
9
+ - ljspeech
10
  license: apache-2.0
11
  ---
12
+
13
+ # ESPnet VITS Text-to-Speech (TTS) Model for ONNX
14
+
15
+ [espnet/kan-bayashi_ljspeech_vits](https://huggingface.co/espnet/kan-bayashi_ljspeech_vits). This model is an ONNX export using the [espnet_onnx](https://github.com/espnet/espnet_onnx) library.
16
+
17
+ ## Usage with txtai
18
+
19
+ txtai has a built in Text to Speech (TTS) pipeline that makes using this model easy.
20
+
21
+ ```python
22
+ ```
23
+
24
+ ## Usage with ONNX
25
+
26
+ This model can also be run directly with ONNX provided the input text is tokenized. Tokenization can be done with [ttstokenizer](https://github.com/neuml/ttstokenizer).
27
+
28
+ ```python
29
+ ```
30
+
31
+ ## How to export
32
+
33
+ More information on how to export ESPnet models to ONNX can be [found here](https://github.com/espnet/espnet_onnx#text2speech-inference).
config.yaml ADDED
@@ -0,0 +1,92 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ normalize:
2
+ use_normalize: false
3
+ text_cleaner:
4
+ cleaner_types: tacotron
5
+ token:
6
+ list:
7
+ - <blank>
8
+ - <unk>
9
+ - AH0
10
+ - N
11
+ - T
12
+ - D
13
+ - S
14
+ - R
15
+ - L
16
+ - DH
17
+ - K
18
+ - Z
19
+ - IH1
20
+ - IH0
21
+ - M
22
+ - EH1
23
+ - W
24
+ - P
25
+ - AE1
26
+ - AH1
27
+ - V
28
+ - ER0
29
+ - F
30
+ - ','
31
+ - AA1
32
+ - B
33
+ - HH
34
+ - IY1
35
+ - UW1
36
+ - IY0
37
+ - AO1
38
+ - EY1
39
+ - AY1
40
+ - .
41
+ - OW1
42
+ - SH
43
+ - NG
44
+ - G
45
+ - ER1
46
+ - CH
47
+ - JH
48
+ - Y
49
+ - AW1
50
+ - TH
51
+ - UH1
52
+ - EH2
53
+ - OW0
54
+ - EY2
55
+ - AO0
56
+ - IH2
57
+ - AE2
58
+ - AY2
59
+ - AA2
60
+ - UW0
61
+ - EH0
62
+ - OY1
63
+ - EY0
64
+ - AO2
65
+ - ZH
66
+ - OW2
67
+ - AE0
68
+ - UW2
69
+ - AH2
70
+ - AY0
71
+ - IY2
72
+ - AW2
73
+ - AA0
74
+ - ''''
75
+ - ER2
76
+ - UH2
77
+ - '?'
78
+ - OY2
79
+ - '!'
80
+ - AW0
81
+ - UH0
82
+ - OY0
83
+ - ..
84
+ - <sos/eos>
85
+ tokenizer:
86
+ g2p_type: g2p_en_no_space
87
+ token_type: phn
88
+ tts_model:
89
+ model_path: espnet/kan-bayashi_ljspeech_vits/full/vits.onnx
90
+ model_type: VITS
91
+ vocoder:
92
+ vocoder_type: not_used
model.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d18b3b99099fcad3bf5b5c02cbc98f262483a72699a9e995833fffbdc445053
3
+ size 137938668