Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- th
|
| 4 |
+
tags:
|
| 5 |
+
- text-to-speech
|
| 6 |
+
- Thai
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
Finetune โมเดลโค้ด GitHub : https://github.com/VYNCX/finetune-local-vits
|
| 10 |
+
|
| 11 |
+
[Finetune-colab](https://colab.research.google.com/drive/12qbpHnu7wYiTEoqh6_57_KUjp4gJkx2h?usp=sharing
|
| 12 |
+
) เทรนโมเดลเสียงด้วยตัวเองบน Google Colab
|
| 13 |
+
|
| 14 |
+
ใช้งาน บน local คอมพิวเตอร์ https://github.com/VYNCX/VachanaTTS
|
| 15 |
+
|
| 16 |
+
การใช้งาน :
|
| 17 |
+
```py
|
| 18 |
+
import torch
|
| 19 |
+
from transformers import VitsTokenizer, VitsModel, set_seed
|
| 20 |
+
import scipy
|
| 21 |
+
|
| 22 |
+
tokenizer = VitsTokenizer.from_pretrained("VIZINTZOR/MMS-TTS-THAI-MALE-PODCAST",cache_dir="./mms")
|
| 23 |
+
model = VitsModel.from_pretrained("VIZINTZOR/MMS-TTS-THAI-MALE-PODCAST",cache_dir="./mms")
|
| 24 |
+
|
| 25 |
+
inputs = tokenizer(text="สวัสดีครับ นี่คือเสียงพูดภาษาไทย", return_tensors="pt")
|
| 26 |
+
|
| 27 |
+
set_seed(456) # make deterministic
|
| 28 |
+
|
| 29 |
+
with torch.no_grad():
|
| 30 |
+
outputs = model(**inputs)
|
| 31 |
+
|
| 32 |
+
waveform = outputs.waveform[0]
|
| 33 |
+
|
| 34 |
+
# Convert PyTorch tensor to NumPy array
|
| 35 |
+
waveform_array = waveform.numpy()
|
| 36 |
+
|
| 37 |
+
scipy.io.wavfile.write("techno_output.wav", rate=model.config.sampling_rate, data=waveform_array)
|
| 38 |
+
```
|