Create README.md
Browse files
README.md
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: transformers
|
3 |
+
pipeline_tag: automatic-speech-recognition
|
4 |
+
license: apache-2.0
|
5 |
+
language:
|
6 |
+
- vi
|
7 |
+
---
|
8 |
+
Converted to Flax from [vinai/PhoWhisper-medium](huggingface.co/vinai/PhoWhisper-medium) for light-speed inference on TPU
|
9 |
+
```py
|
10 |
+
from whisper_jax import FlaxWhisperPipline
|
11 |
+
import jax.numpy as jnp
|
12 |
+
|
13 |
+
pipeline = FlaxWhisperPipline("hr16/PhoWhisper-medium-flax", dtype=jnp.bfloat16, batch_size=16)
|
14 |
+
```
|
15 |
+
|
16 |
+
Original abstract:
|
17 |
+
PhoWhisper: Automatic Speech Recognition for Vietnamese
|
18 |
+
We introduce PhoWhisper in five versions for Vietnamese automatic speech recognition. PhoWhisper's robustness is achieved through fine-tuning the multilingual Whisper on an 844-hour dataset that encompasses diverse Vietnamese accents. Our experimental study demonstrates state-of-the-art performances of PhoWhisper on benchmark Vietnamese ASR datasets. Please cite our PhoWhisper paper when it is used to help produce published results or is incorporated into other software:
|
19 |
+
|
20 |
+
@inproceedings{PhoWhisper,
|
21 |
+
title = {{PhoWhisper: Automatic Speech Recognition for Vietnamese}},
|
22 |
+
author = {Thanh-Thien Le and Linh The Nguyen and Dat Quoc Nguyen},
|
23 |
+
booktitle = {Proceedings of the ICLR 2024 Tiny Papers track},
|
24 |
+
year = {2024}
|
25 |
+
}
|
26 |
+
|
27 |
+
For further information or requests, please go to PhoWhisper's homepage!
|