DevParker
/

VibeVoice7b-low-vram

speech-synthesis

Model card Files Files and versions

VibeVoice7b-low-vram / 4bit

6.63 GB

2 contributors

History: 4 commits

Parker

Upload 5 files

2daa24e verified 5 months ago

QUANTIZATION_README.md
2.92 kB

Upload 5 files 5 months ago
README.md
969 Bytes

Add quantized VibeVoice 7B models (4-bit and 8-bit) 5 months ago
config.json
3.31 kB

Add quantized VibeVoice 7B models (4-bit and 8-bit) 5 months ago
generation_config.json
69 Bytes

Add quantized VibeVoice 7B models (4-bit and 8-bit) 5 months ago
load_quantized_4bit.py
1.83 kB

Add quantized VibeVoice 7B models (4-bit and 8-bit) 5 months ago
minimal_memory_output.wav
314 kB
xet

Upload minimal_memory_output.wav 5 months ago
model-00001-of-00002.safetensors
4.95 GB
xet

Add quantized VibeVoice 7B models (4-bit and 8-bit) 5 months ago
model-00002-of-00002.safetensors
1.68 GB
xet

Add quantized VibeVoice 7B models (4-bit and 8-bit) 5 months ago
model.safetensors.index.json
341 kB

Add quantized VibeVoice 7B models (4-bit and 8-bit) 5 months ago
preprocessor_config.json
294 Bytes

Add quantized VibeVoice 7B models (4-bit and 8-bit) 5 months ago
quantization_config.json
560 Bytes

Add quantized VibeVoice 7B models (4-bit and 8-bit) 5 months ago
quantize_and_save_vibevoice.py
11.1 kB

Upload 5 files 5 months ago
test_accurate_vram.py
6.91 kB

Upload 5 files 5 months ago
use_quantized_model.py
2.15 kB

Upload 5 files 5 months ago
vibevoice_7gb_target.py
6.31 kB

Upload 5 files 5 months ago