Commit
•
499793c
1
Parent(s):
b8808ae
Update README.md
Browse files
README.md
CHANGED
|
@@ -29,20 +29,19 @@ Model can generate Greek text with Greek reference speech, English text with Eng
|
|
| 29 |
|
| 30 |
## Training arguments
|
| 31 |
|
| 32 |
-
Learning Rate: 0.00001
|
| 33 |
-
Batch Size per GPU: 3200
|
| 34 |
-
Max Samples: 64
|
| 35 |
-
Gradient Accumulation Steps: 1
|
| 36 |
-
Max Gradient Norm: 1
|
| 37 |
-
Epochs: 277
|
| 38 |
-
Warmup Updates: 1274
|
| 39 |
-
Save per Updates: 25000
|
| 40 |
-
Last per Steps: 1000
|
| 41 |
-
mixed_precision: fp16
|
| 42 |
|
| 43 |
|
| 44 |
## Links:
|
| 45 |
|
| 46 |
-
Github: https://github.com/SWivid/F5-TTS
|
| 47 |
-
|
| 48 |
-
Paper: F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (https://arxiv.org/abs/2410.06885)
|
|
|
|
| 29 |
|
| 30 |
## Training arguments
|
| 31 |
|
| 32 |
+
- Learning Rate: 0.00001
|
| 33 |
+
- Batch Size per GPU: 3200
|
| 34 |
+
- Max Samples: 64
|
| 35 |
+
- Gradient Accumulation Steps: 1
|
| 36 |
+
- Max Gradient Norm: 1
|
| 37 |
+
- Epochs: 277
|
| 38 |
+
- Warmup Updates: 1274
|
| 39 |
+
- Save per Updates: 25000
|
| 40 |
+
- Last per Steps: 1000
|
| 41 |
+
- mixed_precision: fp16
|
| 42 |
|
| 43 |
|
| 44 |
## Links:
|
| 45 |
|
| 46 |
+
- Github: https://github.com/SWivid/F5-TTS
|
| 47 |
+
- Paper: F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching (https://arxiv.org/abs/2410.06885)
|
|
|