Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,11 @@ On CPU, the model can transcribe a **12-second audio clip in just 0.3 seconds**,
|
|
| 9 |
|
| 10 |
---
|
| 11 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 12 |
## ⚙️ Model Architecture and Training strategy:
|
| 13 |
- **Architecture:** ZipFormer
|
| 14 |
- **Parameters:** ~30M
|
|
@@ -63,11 +68,6 @@ Comprehensive details about **training data**, **optimization strategies**, **ar
|
|
| 63 |
|
| 64 |
---
|
| 65 |
|
| 66 |
-
## 🚀 Online Demo
|
| 67 |
-
|
| 68 |
-
You can try the model directly here:
|
| 69 |
-
👉 https://huggingface.co/spaces/hynt/k2-automatic-speech-recognition-demo
|
| 70 |
-
|
| 71 |
## ⚙️ How to Run This Model
|
| 72 |
|
| 73 |
Please refer to the following guides for instructions on how to run and deploy this model:
|
|
|
|
| 9 |
|
| 10 |
---
|
| 11 |
|
| 12 |
+
## 🚀 Online Demo
|
| 13 |
+
|
| 14 |
+
You can try the model directly here:
|
| 15 |
+
👉 https://huggingface.co/spaces/hynt/k2-automatic-speech-recognition-demo
|
| 16 |
+
|
| 17 |
## ⚙️ Model Architecture and Training strategy:
|
| 18 |
- **Architecture:** ZipFormer
|
| 19 |
- **Parameters:** ~30M
|
|
|
|
| 68 |
|
| 69 |
---
|
| 70 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 71 |
## ⚙️ How to Run This Model
|
| 72 |
|
| 73 |
Please refer to the following guides for instructions on how to run and deploy this model:
|