Downloads · 30 days
21
30% of all-time downloads
sr-corrnet-ss-1ch-aishell1mix-ver1
playwithmino/sr-corrnet-ss-1ch-aishell1mix-ver1
sr-corrnet-ss-1ch-aishell1mix-ver1 is a audio-to-audio model from playwithmino. Use it for the audio-to-audio task on the model card, and read the license before you ship it in a product. It is set up for sr-corrnet. The card lists the license as mit.
Single-channel SR-CorrNet speech separator fine-tuned on AISHELL-1 Mix ver1 (variable 1–5 speakers, mixclean + mixboth).
All-time downloads
71
Public
Repo size
56.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt56.2 MB · 100%
At a glance
- Task
- Audio-to-Audio
- Library
- sr-corrnet
- License
- mit
- Access
- Public
- Created
- Aug 29, 2026
- Updated
- Aug 29, 2026
- SHA
- c7774b4a
Model card
From the Hugging Face model README
SR-CorrNet-SS — AISHELL-1 Mix ver1 (clean + both)
Single-channel SR-CorrNet speech separator fine-tuned on AISHELL-1 Mix ver1 (variable 1–5 speakers, mix_clean + mix_both).
- Architecture: SR-CorrNet-SS (
1ch_aishell1mix_var_2_5spk_clean_both) - Init: English WSJ0 variable 2–5spk
- Checkpoint: exported
best_model.pth(epoch 2) - Code: vu-duy-tung/byd-speech-separation (
recorrnetbranch)
Load
from sr_corrnet import SSInference
model = SSInference.from_pretrained(
"playwithmino/sr-corrnet-ss-1ch-aishell1mix-ver1",
device="cuda:0",
)
result = model.process_file("mix.wav", output_dir="output/")
Files in this repo: model.pt (weights only) and config.yaml.
- Task
- Audio-to-Audio
- Library
- sr-corrnet
- License
- mit
- Created
- Aug 29, 2026
- Updated
- Aug 29, 2026