Vctk Dns2020 Bsrnn Large Noncausal

--- tags: - espnet - audio - audio-to-audio language: en datasets: - VCTK_DEMAND - DNS2020 license: cc-by-4.0 --- ## ESPnet2 ENH model ### `wyz/vctk_dns2020_bsrnn_large_noncausal` This model was trained by wyz based on the universal_se_v1 recipe in [espnet](https://github.com/espnet/espnet/). More information can be found at https://github.com/Emrys365/se-scaling. ### Demo: How to use in ESPnet2 Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html) if you haven't done that already. To use the model in the Python interface, you could use the following code: ```python import soundfile as sf from espnet2.bin.enh_inference import SeparateSpeech # For model downloading + loading model = SeparateSpeech.from_pretrained( model_tag="wyz/vctk_dns2020_bsrnn_large_noncausal", normalize_output_wav=True, device="cuda", ) # For loading a downloaded model # model = SeparateSpeech( # train_config="exp_vctk_dns20/enh_train_enh_bsrnn_large_noncausal_raw/config.yaml", # model_file="exp_vctk_dns20/enh_train_enh_bsrnn_large_noncausal_raw/xxxx.pth", # normalize_output_wav=True, # device="cuda", # ) audio, fs = sf.read("/path/to/noisy/utt1.flac") enhanced = model(audio[None, :], fs=fs)[0] ``` <!-- Generated by ./scripts/utils/show_enh_score.sh --> # RESULTS ## Environments - date: `Tue Feb 27 21:11:00 EST 2024` - python version: `3.8.16 (default, Mar 2 2023, 03:21:46) [GCC 11.2.0]` - espnet version: `espnet 202304` - pytorch version: `pytorch 2.0.1+cu118` - Git hash: `443028662106472c60fe8bd892cb277e5b488651` - Commit date: `Thu May 11 03:32:59 2023 +0000` ## enhanced_test_16k |dataset|PESQ_WB|STOI|SAR|SDR|SIR|SI_SNR|OVRL|SIG|BAK|P808_MOS| |---|---|---|---|---|---|---|---|---|---|---| |chime4_et05_real_isolated_6ch_track|1.17|53.49|-2.58|-2.58|0.00|-30.94|2.93|3.28|3.80|3.68| |chime4_et05_simu_isolated_6ch_track|1.51|84.11|8.57|8.57|0.00|2.50|2.81|3.13|3.86|3.34| |dns20_tt_synthetic_no_reverb|3.22|97.67|19.50|19.50|0.00|19.37|3.32|3.56|4.11|4.01| |reverb_et_real_8ch_multich|2.54|89.28|14.40|14.40|0.00|10.75|2.39|2.91|3.03|3.26| |reverb_et_simu_8ch_multich|1.63|85.72|9.29|9.29|0.00|-10.65|2.62|3.12|3.28|3.53| |whamr_tt_mix_single_reverb_max_16k|1.52|84.78|7.94|7.94|0.00|2.53|2.89|3.28|3.74|3.64| ## enhanced_test_48k |dataset|STOI|SAR|SDR|SIR|SI_SNR|OVRL|SIG|BAK|P808_MOS| |---|---|---|---|---|---|---|---|---|---| |vctk_n...

Source context: 1 downloads · 0 likes · Pipeline audio-to-audio · Library espnet · Repo wyz/vctk_dns2020_bsrnn_large_noncausal