Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
@@ -1,8 +1,11 @@
|
|
1 |
|
2 |
-
---
|
|
|
|
|
3 |
- mms
|
4 |
- vits
|
5 |
-
pipeline_tag: text-to-speech
|
|
|
6 |
|
7 |
# Massively Multilingual Speech (MMS) : Text-to-Speech Models
|
8 |
|
@@ -31,7 +34,6 @@ with torch.no_grad():
|
|
31 |
output = model(**inputs)
|
32 |
|
33 |
from IPython.display import Audio
|
34 |
-
|
35 |
Audio(output.audio[0], rate=16000)
|
36 |
```
|
37 |
|
@@ -43,8 +45,8 @@ Note: For certain checkpoints, the input text must be converted to the Latin alp
|
|
43 |
This model was developed by Vineel Pratap et al. and is licensed as **CC-BY-NC 4.0**
|
44 |
|
45 |
@article{pratap2023mms,
|
46 |
-
title={Scaling Speech Technology to 1,000+ Languages},
|
47 |
-
and Paden Tomasello and Arun Babu and Sayani Kundu and Ali Elkahky and Zhaoheng Ni and Apoorv Vyas and Maryam
|
48 |
-
|
49 |
-
|
50 |
}
|
|
|
1 |
|
2 |
+
---
|
3 |
+
license: cc-by-nc-4.0
|
4 |
+
tags:
|
5 |
- mms
|
6 |
- vits
|
7 |
+
pipeline_tag: text-to-speech
|
8 |
+
---
|
9 |
|
10 |
# Massively Multilingual Speech (MMS) : Text-to-Speech Models
|
11 |
|
|
|
34 |
output = model(**inputs)
|
35 |
|
36 |
from IPython.display import Audio
|
|
|
37 |
Audio(output.audio[0], rate=16000)
|
38 |
```
|
39 |
|
|
|
45 |
This model was developed by Vineel Pratap et al. and is licensed as **CC-BY-NC 4.0**
|
46 |
|
47 |
@article{pratap2023mms,
|
48 |
+
title={Scaling Speech Technology to 1,000+ Languages},
|
49 |
+
author={Vineel Pratap and Andros Tjandra and Bowen Shi and Paden Tomasello and Arun Babu and Sayani Kundu and Ali Elkahky and Zhaoheng Ni and Apoorv Vyas and Maryam Fazel-Zarandi and Alexei Baevski and Yossi Adi and Xiaohui Zhang and Wei-Ning Hsu and Alexis Conneau and Michael Auli},
|
50 |
+
journal={arXiv},
|
51 |
+
year={2023}
|
52 |
}
|