Tfgridnet For Urgent24

--- tags: - audio - audio-to-audio language: en datasets: - urgent24 license: cc-by-4.0 library_name: espnet --- ## ESPnet2 ENH model ### `wyz/tfgridnet_for_urgent24` This model was trained by Wangyou Zhang using the [urgent24](https://github.com/espnet/espnet/blob/master/egs2/urgent24/enh1) recipe in [espnet](https://github.com/espnet/espnet/). This model is provided as a pre-trained baseline model for the [URGENT 2024 Challenge](https://urgent-challenge.github.io/urgent2024). ### 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. ```bash cd espnet pip install -e . cd egs2/urgent24/enh1 ./run.sh --skip_data_prep false --skip_train true --is_tse_task true --download_model wyz/tfgridnet_for_urgent24 ``` To use the model in the Python interface, you could use the following code: > Please make sure you are using the latest ESPnet by installing from the source: > ``` > python -m pip install git+https://github.com/espnet/espnet > ``` ```python import soundfile as sf from espnet2.bin.enh_inference import SeparateSpeech # For model downloading + loading model = SeparateSpeech.from_pretrained( model_tag="wyz/tfgridnet_for_urgent24", normalize_output_wav=True, device="cuda", ) # For loading a downloaded model # model = SeparateSpeech( # train_config="exp/xxx/config.yaml", # model_file="exp/xx/valid.loss.best.pth", # normalize_output_wav=True, # device="cuda", # ) audio, fs = sf.read("/path/to/noisy/utt1.flac") enhanced = model(audio[None, :], fs=fs)[0] ``` ## ENH config <details><summary>expand</summary> ``` config: conf/tuning/train_enh_tfgridnet.yaml print_config: false log_level: INFO drop_last_iter: false dry_run: false iterator_type: chunk valid_iterator_type: null output_dir: exp/enh_train_enh_tfgridnet_raw ngpu: 1 seed: 0 num_workers: 4 num_att_plot: 3 dist_backend: nccl dist_init_method: env:// dist_world_size: 4 dist_rank: 0 local_rank: 0 dist_master_addr: localhost dist_master_port: 54825 dist_launcher: null multiprocessing_distributed: true unused_parameters: true sharded_ddp: false cudnn_enabled: true cudnn_benchmark: false cudnn_deterministic: true collect_stats: false write_collected_feats: false max_epoch: 100 patience: 40 val_scheduler_criterion: - valid - loss early_stopping_criterion: - valid - loss - min best_model_criter...

Source context: 20 downloads · 4 likes · Pipeline audio-to-audio · Library espnet · Repo wyz/tfgridnet_for_urgent24