Commit
•
ebb8ff9
1
Parent(s):
6155c4f
Update README.md
Browse files
README.md
CHANGED
|
@@ -23,8 +23,19 @@ transcriptions = asr_model.transcribe(["file.wav"])
|
|
| 23 |
```
|
| 24 |
## Training Datasets
|
| 25 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
## Training Details
|
| 27 |
|
|
|
|
|
|
|
| 28 |
## Evaluation
|
| 29 |
|
| 30 |
|
|
|
|
| 23 |
```
|
| 24 |
## Training Datasets
|
| 25 |
|
| 26 |
+
| Channels Category | Hours |
|
| 27 |
+
| ----------------- | ----------- |
|
| 28 |
+
| News | 17,640.00 |
|
| 29 |
+
| Talkshow | 688.82 |
|
| 30 |
+
| Vlog | 0.02 |
|
| 31 |
+
| Crime Show | 4.08 |
|
| 32 |
+
| Total | 18,332.92 |
|
| 33 |
+
|
| 34 |
+
|
| 35 |
## Training Details
|
| 36 |
|
| 37 |
+
For training the model, the dataset we selected comprises 17.64k hours of news chan- nel content, 688.82 hours of talk shows, 0.02 hours of vlogs, and 4.08 hours of crime shows.
|
| 38 |
+
|
| 39 |
## Evaluation
|
| 40 |
|
| 41 |
|