Downloads · 30 days
10
4% of all-time downloads
espnet/yen-ju-lu-dns_ins20_enh_train_enh_blstm_tf_raw_valid.loss.best
yen-ju-lu-dns_ins20_enh_train_enh_blstm_tf_raw_valid.loss.best is a audio-to-audio model from espnet. 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 espnet. The card lists the license as cc-by-4.0.
♻️ Imported from <https://zenodo.org/record/4923697.YOAOIpozZH4.
Downloads · 30 days
10
4% of all-time downloads
All-time downloads
244
Public
Repo size
191 MB
Likes
1
Public
Click a slice to open those files.
.pth191 MB · 100%
From the Hugging Face model README
pip install espnet
espnet enhance noisy.wav -o enhanced.wav --model espnet/yen-ju-lu-dns_ins20_enh_train_enh_blstm_tf_raw_valid.loss.best
import soundfile as sf
from espnet2.bin.enh_inference import SeparateSpeech
enh = SeparateSpeech.from_pretrained(model_tag="espnet/yen-ju-lu-dns_ins20_enh_train_enh_blstm_tf_raw_valid.loss.best")
# channels are kept on the way in: a multi-channel model needs them
speech, rate = sf.read("noisy.wav", dtype="float32")
waves = enh(speech[None, ...], fs=rate)
# one wave per output stream, which is what tells the two tasks apart: an
# enhancement model returns one, a separation model one per speaker. This is
# what `espnet enhance` writes as enhanced.wav or enhanced.spk1.wav, ...
if len(waves) == 1:
sf.write("enhanced.wav", waves[0][0], rate)
else:
for i, wave in enumerate(waves, start=1):
sf.write(f"enhanced.spk{i}.wav", wave[0], rate)
neillu23/dns_ins20_enh_train_enh_blstm_tf_raw_valid.loss.best, fs=16k, lang=en♻️ Imported from https://zenodo.org/record/4923697#.YOAOIpozZH4.
This model was trained by neillu23 using dns_ins20 recipe in espnet.
See https://github.com/espnet/espnet_model_zoo
# coming soon
# RESULTS
## Environments
- date: `Wed Jun 9 09:49:34 CST 2021`
- python version: `3.8.10 (default, May 19 2021, 18:05:58) [GCC 7.3.0]`
- espnet version: `espnet 0.9.9`
- pytorch version: `pytorch 1.4.0`
- Git hash: `c1dfefb98bf59f654e0907b9681668eaca8ddfcc`
- Commit date: `Tue Jun 8 17:23:26 2021 +0800`
## enh_train_enh_blstm_tf_raw
config: ./conf/tuning/train_enh_blstm_tf.yaml
|dataset|STOI|SAR|SDR|SIR|
|---|---|---|---|---|
|enhanced_cv_synthetic|0.98|23.87|23.87|0.00|
|enhanced_tt_synthetic_no_reverb|0.96|15.94|15.94|0.00|
|enhanced_tt_synthetic_with_reverb|0.84|11.86|11.86|0.00|
See full config in config.yaml
config: ./conf/tuning/train_enh_blstm_tf.yaml
print_config: false
log_level: INFO
dry_run: false
iterator_type: sequence
output_dir: exp/enh_train_enh_blstm_tf_raw
ngpu: 1
seed: 0
num_workers: 4
num_att_plot: 3
dist_backend: nccl
dist_init_method: env://
dist_world_size: 2
dist_rank: 0
local_rank: 0
dist_master_addr: localhost
dist_master_port: 45398
dist_launcher: null
multiprocessing_distributed: true
unused_parameters: false
sharded_ddp: false
cudnn_enabled: true
cudnn_benchmark: false
cudnn_deterministic: true