Update README.md
Browse files
README.md
CHANGED
|
@@ -13,9 +13,10 @@ import jax.numpy as jnp
|
|
| 13 |
pipeline = FlaxWhisperPipline("hr16/PhoWhisper-large-flax", dtype=jnp.bfloat16, batch_size=16)
|
| 14 |
```
|
| 15 |
|
| 16 |
-
|
| 17 |
-
|
| 18 |
-
|
|
|
|
| 19 |
|
| 20 |
```
|
| 21 |
@inproceedings{PhoWhisper,
|
|
@@ -26,4 +27,4 @@ We introduce PhoWhisper in five versions for Vietnamese automatic speech recogni
|
|
| 26 |
}
|
| 27 |
```
|
| 28 |
|
| 29 |
-
For further information or requests, please go to PhoWhisper's homepage!
|
|
|
|
| 13 |
pipeline = FlaxWhisperPipline("hr16/PhoWhisper-large-flax", dtype=jnp.bfloat16, batch_size=16)
|
| 14 |
```
|
| 15 |
|
| 16 |
+
# PhoWhisper: Automatic Speech Recognition for Vietnamese
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
We introduce **PhoWhisper** in five versions for Vietnamese automatic speech recognition. PhoWhisper's robustness is achieved through fine-tuning the multilingual [Whisper](https://github.com/openai/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:
|
| 20 |
|
| 21 |
```
|
| 22 |
@inproceedings{PhoWhisper,
|
|
|
|
| 27 |
}
|
| 28 |
```
|
| 29 |
|
| 30 |
+
For further information or requests, please go to [PhoWhisper's homepage](https://github.com/VinAIResearch/PhoWhisper)!
|