Vctk Dns2020 Bsrnn Large Double 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_double_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_double_noncausal", normalize_output_wav=True, device="cuda", ) # For loading a downloaded model # model = SeparateSpeech( # train_config="exp_vctk_dns20/enh_train_enh_bsrnn_large_double_noncausal_raw/config.yaml", # model_file="exp_vctk_dns20/enh_train_enh_bsrnn_large_double_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: `Sat Mar 9 22:39:41 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|53.69|-2.56|-2.56|0.00|-30.93|2.98|3.30|3.87|3.70| |chime4_et05_simu_isolated_6ch_track|1.51|84.94|8.69|8.69|0.00|2.58|2.88|3.17|3.92|3.39| |dns20_tt_synthetic_no_reverb|3.27|97.88|19.59|19.59|0.00|19.63|3.31|3.55|4.10|4.02| |reverb_et_real_8ch_multich|1.56|78.03|8.41|8.41|0.00|5.01|2.82|3.23|3.64|3.63| |reverb_et_simu_8ch_multich|1.64|85.85|9.38|9.38|0.00|-10.66|2.75|3.23|3.46|3.63| |whamr_tt_mix_single_reverb_max_16k|1.55|85.94|7.91|7.91|0.00|2.59|2.95|3.30|3.81|3.67| ## enhanced_test_48k |dataset|STOI|SAR|SDR|SIR|SI_SNR|OVRL|SIG|BAK|P808_MOS| |---|---|---|---|---|---|--...

Source context: 6 downloads · 0 likes · Pipeline audio-to-audio · Library espnet · Repo wyz/vctk_dns2020_bsrnn_large_double_noncausal