Update README.md
Browse files
README.md
CHANGED
|
@@ -31,6 +31,23 @@ for segment in segments:
|
|
| 31 |
print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
|
| 32 |
```
|
| 33 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 34 |
## Conversion details
|
| 35 |
|
| 36 |
The original model was converted with the following command:
|
|
|
|
| 31 |
print("[%.2fs -> %.2fs] %s" % (segment.start, segment.end, segment.text))
|
| 32 |
```
|
| 33 |
|
| 34 |
+
### Benchmark
|
| 35 |
+
We measure the inference speed with four different Japanese speech audio on MacBook Pro with the following spec:
|
| 36 |
+
- Apple M2 Pro
|
| 37 |
+
- 32GB
|
| 38 |
+
- 14-inch, 2023
|
| 39 |
+
- OS Sonoma Version 14.4.1 (23E224)
|
| 40 |
+
|
| 41 |
+
|
| 42 |
+
|
| 43 |
+
| audio file | audio duration (min)| inference time (sec) |
|
| 44 |
+
|--|---------------------|-------------|
|
| 45 |
+
|audio 1 | 50.3 | 2601 |
|
| 46 |
+
|audio 2 | 5.6 | 73 |
|
| 47 |
+
|audio 3 | 4.9 | 141 |
|
| 48 |
+
|audio 4 | 5.6 | 126 |
|
| 49 |
+
|
| 50 |
+
|
| 51 |
## Conversion details
|
| 52 |
|
| 53 |
The original model was converted with the following command:
|