Downloads · 30 days
1.1K
10% of all-time downloads
MMS-TTS-THAI-FEMALEV2
VIZINTZOR/MMS-TTS-THAI-FEMALEV2
MMS-TTS-THAI-FEMALEV2 is a text-to-speech model from VIZINTZOR. Use it when you need text read aloud.
Finetune โมเดลโค้ด GitHub : https://github.com/VYNCX/finetune-local-vits
All-time downloads
11.2K
Public
Parameters
86.4M
346 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors346 MB · 100%
At a glance
- Task
- Text-to-Speech
- Model type
- vits
- Access
- Public
- Created
- Feb 21, 2025
- Updated
- Nov 2, 2025
- SHA
- 236e33ca
Model card
From the Hugging Face model README
Finetune โมเดลโค้ด GitHub : https://github.com/VYNCX/finetune-local-vits
Finetune-colab เทรนโมเดลเสียงด้วยตัวเองบน Google Colab
ใช้งาน บน local คอมพิวเตอร์ https://github.com/VYNCX/VachanaTTS
การใช้งาน :
import torch
from transformers import VitsTokenizer, VitsModel, set_seed
import scipy
tokenizer = VitsTokenizer.from_pretrained("VIZINTZOR/MMS-TTS-THAI-FEMALEV2",cache_dir="./mms")
model = VitsModel.from_pretrained("VIZINTZOR/MMS-TTS-THAI-FEMALEV2",cache_dir="./mms")
inputs = tokenizer(text="สวัสดีค่ะ นี่คือเสียงพูดภาษาไทย", return_tensors="pt")
set_seed(456) # make deterministic
with torch.no_grad():
outputs = model(**inputs)
waveform = outputs.waveform[0]
# Convert PyTorch tensor to NumPy array
waveform_array = waveform.numpy()
scipy.io.wavfile.write("techno_output.wav", rate=model.config.sampling_rate, data=waveform_array)
- Task
- Text-to-Speech
- Type
- vits
- Languages
- th
- Created
- Feb 21, 2025
- Updated
- Nov 2, 2025