Vctk Dns2020 Bsrnn Medium 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_medium_noncausal` This model was trained by wyz using 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_medium_noncausal", normalize_output_wav=True, device="cuda", ) # For loading a downloaded model # model = SeparateSpeech( # train_config="exp_vctk_dns20/enh_train_enh_bsrnn_medium_noncausal_raw/config.yaml", # model_file="exp_vctk_dns20/enh_train_enh_bsrnn_medium_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 22:36:44 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|1.19|53.80|-2.46|-2.46|0.00|-31.04|3.07|3.40|3.91|3.72| |chime4_et05_simu_isolated_6ch_track|1.58|84.56|9.02|9.02|0.00|2.74|2.94|3.25|3.92|3.33| |dns20_tt_synthetic_no_reverb|3.28|97.86|19.82|19.82|0.00|19.74|3.35|3.59|4.13|4.03| |reverb_et_real_8ch_multich|1.74|82.86|10.32|10.32|0.00|6.55|2.73|3.20|3.53|3.51| |reverb_et_simu_8ch_multich|1.62|85.32|9.20|9.20|0.00|-10.54|2.78|3.27|3.49|3.60| |whamr_tt_mix_single_reverb_max_16k|1.56|85.42|8.02|8.02|0.00|2.64|2.98|3.34|3.83|3.68| ## enhanced_test_48k |dataset|STOI|SAR|SDR|SIR|SI_SNR|OVRL|SIG|BAK|P808_MOS| |---|---|---|---|---|---|---|---|---|---| |vctk_noisy...

Source context: 2 downloads · 0 likes · Pipeline audio-to-audio · Library espnet · Repo wyz/vctk_dns2020_bsrnn_medium_noncausal