Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# U-CTC
|
| 2 |
**U-CTC** is an Urdu automatic speech recognition (ASR) model based on the [Parakeet-CTC-0.6B](https://huggingface.co/nvidia/parakeet-ctc-0.6b) architecture. It has been fine-tuned on ~21 hours of Urdu speech data using the NVIDIA NeMo framework. The model is optimized for CTC-based transcription of spoken Urdu.
|
| 3 |
|
|
@@ -65,6 +72,4 @@ The model was trained and evaluated on a manually curated Urdu speech dataset:
|
|
| 65 |
---
|
| 66 |
## Comparison with OpenAI Whisper (Base / Medium)
|
| 67 |
|
| 68 |
-
---
|
| 69 |
-
|
| 70 |
-
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: cc-by-4.0
|
| 3 |
+
language:
|
| 4 |
+
- ur
|
| 5 |
+
base_model:
|
| 6 |
+
- nvidia/parakeet-ctc-0.6b
|
| 7 |
+
---
|
| 8 |
# U-CTC
|
| 9 |
**U-CTC** is an Urdu automatic speech recognition (ASR) model based on the [Parakeet-CTC-0.6B](https://huggingface.co/nvidia/parakeet-ctc-0.6b) architecture. It has been fine-tuned on ~21 hours of Urdu speech data using the NVIDIA NeMo framework. The model is optimized for CTC-based transcription of spoken Urdu.
|
| 10 |
|
|
|
|
| 72 |
---
|
| 73 |
## Comparison with OpenAI Whisper (Base / Medium)
|
| 74 |
|
| 75 |
+
---
|
|
|
|
|
|