Model reference · open weights
DPRNNTasNet-ks2_WHAM_sepclean is an open-weight audio or speech model from mpariente. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.
Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.
What it is
| Maker | mpariente |
|---|---|
| Type | Audio & music |
| Task | Audio→audio |
| Runs with | asteroid |
| Released | 2022-03-02 |
| Popularity | 868 downloads / month |
| Licence | Open weights |
About
mpariente/DPRNNTasNet-ks2_WHAM_sepcleanImported from Zenodo
This model was trained by Manuel Pariente
using the wham/DPRNN recipe in Asteroid.
It was trained on the sep_clean task of the WHAM! dataset.
data:
mode: min
nondefault_nsrc: None
sample_rate: 8000
segment: 2.0
task: sep_clean
train_dir: data/wav8k/min/tr
valid_dir: data/wav8k/min/cv
filterbank:
kernel_size: 2
n_filters: 64
stride: 1
main_args:
exp_dir: exp/train_dprnn_new/
gpus: -1
help: None
masknet:
bidirectional: True
bn_chan: 128
chunk_size: 250
dropout: 0
hid_size: 128
hop_size: 125
in_chan: 64
mask_act: sigmoid
n_repeats: 6
n_src: 2
out_chan: 64
optim:
lr: 0.001
optimizer: adam
weight_decay: 1e-05
positional arguments:
training:
batch_size: 3
early_stop: True
epochs: 200
gradient_clipping: 5
half_lr: True
num_workers: 8
si_sdr: 19.316743490695334
si_sdr_imp: 19.317895273889842
sdr: 19.68085347190952
sdr_imp: 19.5298092932871
sir: 30.362213998701232
sir_imp: 30.21116982007881
sar: 20.15553251343315
sar_imp: -129.02091762351188
stoi: 0.97772664309074
stoi_imp: 0.23968091518217424
This work "DPRNNTasNet-ks2_WHAM_sepclean" is a derivative of CSR-I (WSJ0) Complete by LDC, used under LDC User Agreement for Non-Members (Research only). "DPRNNTasNet-ks2_WHAM_sepclean" is licensed under Attribution-ShareAlike 3.0 Unported by Manuel Pariente.
From the published model card. Full card on the HuggingFace links in the sidebar.
How it works
Using it via the API
Once AxForge deploys dprnntasnet-ks2-wham-sepclean for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (dprnntasnet-ks2-wham-sepclean below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="dprnntasnet-ks2-wham-sepclean" -F file=@audio.mp3
Create an account — your API key is available in the console. 5M tokens/month currently included with every new account at launch.