DevParker
/

VibeVoice7b-low-vram

speech-synthesis

Model card Files Files and versions

VibeVoice7b-low-vram / 4bit

Ctrl+K

Ctrl+K

2 contributors

History: 4 commits

Parker

Upload 5 files

2daa24e verified 3 days ago

QUANTIZATION_README.md

2.92 kB

Upload 5 files 3 days ago
README.md

969 Bytes

Add quantized VibeVoice 7B models (4-bit and 8-bit) 3 days ago
config.json

3.31 kB

Add quantized VibeVoice 7B models (4-bit and 8-bit) 3 days ago
generation_config.json

69 Bytes

Add quantized VibeVoice 7B models (4-bit and 8-bit) 3 days ago
load_quantized_4bit.py

1.83 kB

Add quantized VibeVoice 7B models (4-bit and 8-bit) 3 days ago
minimal_memory_output.wav

314 kB
xet

Upload minimal_memory_output.wav 3 days ago
model-00001-of-00002.safetensors

4.95 GB
xet

Add quantized VibeVoice 7B models (4-bit and 8-bit) 3 days ago
model-00002-of-00002.safetensors

1.68 GB
xet

Add quantized VibeVoice 7B models (4-bit and 8-bit) 3 days ago
model.safetensors.index.json

341 kB

Add quantized VibeVoice 7B models (4-bit and 8-bit) 3 days ago
preprocessor_config.json

294 Bytes

Add quantized VibeVoice 7B models (4-bit and 8-bit) 3 days ago
quantization_config.json

560 Bytes

Add quantized VibeVoice 7B models (4-bit and 8-bit) 3 days ago
quantize_and_save_vibevoice.py

11.1 kB

Upload 5 files 3 days ago
test_accurate_vram.py

6.91 kB

Upload 5 files 3 days ago
use_quantized_model.py

2.15 kB

Upload 5 files 3 days ago
vibevoice_7gb_target.py

6.31 kB

Upload 5 files 3 days ago