Commit
•
62526e7
1
Parent(s):
7aa1d35
Add model files
Browse files- README.md +30 -0
- config.yaml +97 -0
- model.onnx +3 -0
README.md
CHANGED
|
@@ -1,3 +1,33 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
---
|
| 2 |
+
tags:
|
| 3 |
+
- espnet
|
| 4 |
+
- audio
|
| 5 |
+
- text-to-speech
|
| 6 |
+
- onnx
|
| 7 |
+
language: en
|
| 8 |
+
datasets:
|
| 9 |
+
- ljspeech
|
| 10 |
license: apache-2.0
|
| 11 |
---
|
| 12 |
+
|
| 13 |
+
# ESPnet JETS Text-to-Speech (TTS) Model for ONNX
|
| 14 |
+
|
| 15 |
+
[imdanboy/jets](https://huggingface.co/imdanboy/jets) exported to ONNX. 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 +1,97 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
normalize:
|
| 2 |
+
eps: 1.0e-20
|
| 3 |
+
norm_means: true
|
| 4 |
+
norm_vars: true
|
| 5 |
+
stats_file: imdanboy/ljspeech_tts_train_jets_raw_phn_tacotron_g2p_en_no_space_train.total_count.ave/feats_stats.npz
|
| 6 |
+
type: gmvn
|
| 7 |
+
use_normalize: true
|
| 8 |
+
text_cleaner:
|
| 9 |
+
cleaner_types: tacotron
|
| 10 |
+
token:
|
| 11 |
+
list:
|
| 12 |
+
- <blank>
|
| 13 |
+
- <unk>
|
| 14 |
+
- AH0
|
| 15 |
+
- N
|
| 16 |
+
- T
|
| 17 |
+
- D
|
| 18 |
+
- S
|
| 19 |
+
- R
|
| 20 |
+
- L
|
| 21 |
+
- DH
|
| 22 |
+
- K
|
| 23 |
+
- Z
|
| 24 |
+
- IH1
|
| 25 |
+
- IH0
|
| 26 |
+
- M
|
| 27 |
+
- EH1
|
| 28 |
+
- W
|
| 29 |
+
- P
|
| 30 |
+
- AE1
|
| 31 |
+
- AH1
|
| 32 |
+
- V
|
| 33 |
+
- ER0
|
| 34 |
+
- F
|
| 35 |
+
- ','
|
| 36 |
+
- AA1
|
| 37 |
+
- B
|
| 38 |
+
- HH
|
| 39 |
+
- IY1
|
| 40 |
+
- UW1
|
| 41 |
+
- IY0
|
| 42 |
+
- AO1
|
| 43 |
+
- EY1
|
| 44 |
+
- AY1
|
| 45 |
+
- .
|
| 46 |
+
- OW1
|
| 47 |
+
- SH
|
| 48 |
+
- NG
|
| 49 |
+
- G
|
| 50 |
+
- ER1
|
| 51 |
+
- CH
|
| 52 |
+
- JH
|
| 53 |
+
- Y
|
| 54 |
+
- AW1
|
| 55 |
+
- TH
|
| 56 |
+
- UH1
|
| 57 |
+
- EH2
|
| 58 |
+
- OW0
|
| 59 |
+
- EY2
|
| 60 |
+
- AO0
|
| 61 |
+
- IH2
|
| 62 |
+
- AE2
|
| 63 |
+
- AY2
|
| 64 |
+
- AA2
|
| 65 |
+
- UW0
|
| 66 |
+
- EH0
|
| 67 |
+
- OY1
|
| 68 |
+
- EY0
|
| 69 |
+
- AO2
|
| 70 |
+
- ZH
|
| 71 |
+
- OW2
|
| 72 |
+
- AE0
|
| 73 |
+
- UW2
|
| 74 |
+
- AH2
|
| 75 |
+
- AY0
|
| 76 |
+
- IY2
|
| 77 |
+
- AW2
|
| 78 |
+
- AA0
|
| 79 |
+
- ''''
|
| 80 |
+
- ER2
|
| 81 |
+
- UH2
|
| 82 |
+
- '?'
|
| 83 |
+
- OY2
|
| 84 |
+
- '!'
|
| 85 |
+
- AW0
|
| 86 |
+
- UH0
|
| 87 |
+
- OY0
|
| 88 |
+
- ..
|
| 89 |
+
- <sos/eos>
|
| 90 |
+
tokenizer:
|
| 91 |
+
g2p_type: g2p_en_no_space
|
| 92 |
+
token_type: phn
|
| 93 |
+
tts_model:
|
| 94 |
+
model_path: imdanboy/ljspeech_tts_train_jets_raw_phn_tacotron_g2p_en_no_space_train.total_count.ave/full/jets.onnx
|
| 95 |
+
model_type: JETS
|
| 96 |
+
vocoder:
|
| 97 |
+
vocoder_type: not_used
|
model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f8222def33152135d49b4a27dff203c24c2c6c68a7fcaf2b649475ac2fe0c871
|
| 3 |
+
size 132537001
|