Update README.md
Browse files
README.md
CHANGED
|
@@ -52,6 +52,13 @@ pipeline_tag: automatic-speech-recognition
|
|
| 52 |
TrorYongASR is an Encoder-Decoder model for Automatic Speech Recognition (ASR) task.
|
| 53 |
It is inspired by [PARSeq](https://github.com/baudm/parseq/tree/main) and [Whisper](https://github.com/openai/whisper/tree/main): the auditory-lingual decoder has only one transformer block.
|
| 54 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
<div align="center">
|
| 56 |
|
| 57 |
| **Model Size** | Tiny | Small |
|
|
|
|
| 52 |
TrorYongASR is an Encoder-Decoder model for Automatic Speech Recognition (ASR) task.
|
| 53 |
It is inspired by [PARSeq](https://github.com/baudm/parseq/tree/main) and [Whisper](https://github.com/openai/whisper/tree/main): the auditory-lingual decoder has only one transformer block.
|
| 54 |
|
| 55 |
+
<div align="center">
|
| 56 |
+
<picture>
|
| 57 |
+
<img src="figures/architecture.png" width="100%" alt="TrorYongASR">
|
| 58 |
+
</picture>
|
| 59 |
+
</div>
|
| 60 |
+
|
| 61 |
+
TrorYongASR has **2 configurations**:
|
| 62 |
<div align="center">
|
| 63 |
|
| 64 |
| **Model Size** | Tiny | Small |
|