Update citation and code links
Browse files
README.md
CHANGED
@@ -8,17 +8,14 @@ tags:
|
|
8 |
- speech-to-speech-translation
|
9 |
|
10 |
datasets:
|
11 |
-
-
|
12 |
-
- covost2
|
13 |
-
- europarl_st
|
14 |
-
- voxpopuli
|
15 |
|
16 |
---
|
17 |
## xm_transformer_s2ut_en-hk
|
18 |
|
19 |
-
Speech-to-speech translation model from fairseq
|
20 |
- English-Hokkien
|
21 |
-
- Trained on
|
22 |
- Speech synthesis with [facebook/unit_hifigan_HK_layer12.km2500_frame_TAT-TTS](https://huggingface.co/facebook/unit_hifigan_HK_layer12.km2500_frame_TAT-TTS)
|
23 |
|
24 |
## Usage
|
@@ -87,18 +84,4 @@ tts_sample = tts_model.get_model_input(unit)
|
|
87 |
wav, sr = tts_model.get_prediction(tts_sample)
|
88 |
|
89 |
ipd.Audio(wav, rate=sr)
|
90 |
-
```
|
91 |
-
|
92 |
-
## Citation
|
93 |
-
```bibtex
|
94 |
-
@misc{https://doi.org/10.48550/arxiv.2204.02967,
|
95 |
-
doi = {10.48550/ARXIV.2204.02967},
|
96 |
-
url = {https://arxiv.org/abs/2204.02967},
|
97 |
-
author = {Popuri, Sravya and Chen, Peng-Jen and Wang, Changhan and Pino, Juan and Adi, Yossi and Gu, Jiatao and Hsu, Wei-Ning and Lee, Ann},
|
98 |
-
keywords = {Computation and Language (cs.CL), Sound (cs.SD), Audio and Speech Processing (eess.AS), FOS: Computer and information sciences, FOS: Computer and information sciences, FOS: Electrical engineering, electronic engineering, information engineering, FOS: Electrical engineering, electronic engineering, information engineering},
|
99 |
-
title = {Enhanced Direct Speech-to-Speech Translation Using Self-supervised Pre-training and Data Augmentation},
|
100 |
-
publisher = {arXiv},
|
101 |
-
year = {2022},
|
102 |
-
copyright = {arXiv.org perpetual, non-exclusive license}
|
103 |
-
}
|
104 |
```
|
|
|
8 |
- speech-to-speech-translation
|
9 |
|
10 |
datasets:
|
11 |
+
- MuST-C
|
|
|
|
|
|
|
12 |
|
13 |
---
|
14 |
## xm_transformer_s2ut_en-hk
|
15 |
|
16 |
+
Speech-to-speech translation model from fairseq:
|
17 |
- English-Hokkien
|
18 |
+
- Trained on MuST-C
|
19 |
- Speech synthesis with [facebook/unit_hifigan_HK_layer12.km2500_frame_TAT-TTS](https://huggingface.co/facebook/unit_hifigan_HK_layer12.km2500_frame_TAT-TTS)
|
20 |
|
21 |
## Usage
|
|
|
84 |
wav, sr = tts_model.get_prediction(tts_sample)
|
85 |
|
86 |
ipd.Audio(wav, rate=sr)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
87 |
```
|