Update README.md
Browse files
README.md
CHANGED
|
@@ -27,4 +27,13 @@ pipeline_tag: automatic-speech-recognition
|
|
| 27 |
|
| 28 |
|
| 29 |
|
| 30 |
-
The fine-tuned Whisper models and Speech-LLM we proposed.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 27 |
|
| 28 |
|
| 29 |
|
| 30 |
+
The fine-tuned Whisper models and Speech-LLM we proposed.
|
| 31 |
+
| **System** | **Dev** | **Eval** | **CV-Test** |
|
| 32 |
+
|----------------------------|---------|----------|-------------|
|
| 33 |
+
| Whisper (LoRA-fine-tuned) | 11.40 | 10.71 | **11.47** |
|
| 34 |
+
| Whisper (Full-fine-tuned) | 10.99 | 10.07 | 13.11 |
|
| 35 |
+
| mHuBERT (CTC) | 29.67 | 19.99 | 68.49 |
|
| 36 |
+
| NTU-Speechlab | 11.57 | 10.58 | - |
|
| 37 |
+
| Seewoo | 12.73 | 11.57 | - |
|
| 38 |
+
| SHNU-mASR | 13.39 | 11.43 | 19.86 |
|
| 39 |
+
| **Proposed Speech-LLM** | 11.74 | **10.69**| 15.26 |
|