sravyapopuri388
commited on
Commit
•
a8ec889
1
Parent(s):
6918b4c
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
## Usage
|
2 |
```python
|
3 |
from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf_hub
|
@@ -36,3 +61,5 @@ wav, sr = TTSHubInterface.get_prediction(
|
|
36 |
)
|
37 |
|
38 |
ipd.Audio(wav, rate=rate)
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: fairseq
|
3 |
+
task: audio-to-audio
|
4 |
+
tags:
|
5 |
+
- fairseq
|
6 |
+
- audio
|
7 |
+
- audio-to-audio
|
8 |
+
- speech-to-speech-translation
|
9 |
+
|
10 |
+
datasets:
|
11 |
+
- mtedx
|
12 |
+
- covost2
|
13 |
+
- europarl_st
|
14 |
+
- voxpopuli
|
15 |
+
widget:
|
16 |
+
- example_title: Common Voice sample 1
|
17 |
+
src: https://huggingface.co/facebook/xm_transformer_600m-es_en-multi_domain/resolve/main/common_voice_es_19966634.flac
|
18 |
+
---
|
19 |
+
# xm_transformer_600m-es_en-multi_domain
|
20 |
+
|
21 |
+
[W2V2-Transformer](https://aclanthology.org/2021.acl-long.68/) speech-to-text translation model from fairseq S2T ([paper](https://arxiv.org/abs/2010.05171)/[code](https://github.com/pytorch/fairseq/tree/main/examples/speech_to_text)):
|
22 |
+
- Spanish-English
|
23 |
+
- Trained on mTEDx, CoVoST 2, EuroParl-ST, VoxPopuli, Multilingual LibriSpeech, Common Voice v7 and CCMatrix
|
24 |
+
- Speech synthesis with [facebook/fastspeech2-en-ljspeech](https://huggingface.co/facebook/fastspeech2-en-ljspeech)
|
25 |
+
|
26 |
## Usage
|
27 |
```python
|
28 |
from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf_hub
|
|
|
61 |
)
|
62 |
|
63 |
ipd.Audio(wav, rate=rate)
|
64 |
+
```
|
65 |
+
|