February 4, 2021 Other Open Access

Chenda Li

DCAT Export

<?xml version='1.0' encoding='utf-8'?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:adms="http://www.w3.org/ns/adms#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:dct="http://purl.org/dc/terms/" xmlns:dctype="http://purl.org/dc/dcmitype/" xmlns:dcat="http://www.w3.org/ns/dcat#" xmlns:duv="http://www.w3.org/ns/duv#" xmlns:foaf="http://xmlns.com/foaf/0.1/" xmlns:frapo="http://purl.org/cerif/frapo/" xmlns:geo="http://www.w3.org/2003/01/geo/wgs84_pos#" xmlns:gsp="http://www.opengis.net/ont/geosparql#" xmlns:locn="http://www.w3.org/ns/locn#" xmlns:org="http://www.w3.org/ns/org#" xmlns:owl="http://www.w3.org/2002/07/owl#" xmlns:prov="http://www.w3.org/ns/prov#" xmlns:rdfs="http://www.w3.org/2000/01/rdf-schema#" xmlns:schema="http://schema.org/" xmlns:skos="http://www.w3.org/2004/02/skos/core#" xmlns:vcard="http://www.w3.org/2006/vcard/ns#" xmlns:wdrs="http://www.w3.org/2007/05/powder-s#">
  <rdf:Description rdf:about="https://doi.org/10.5281/zenodo.4498562">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.4498562</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.4498562"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>Chenda Li</foaf:name>
      </rdf:Description>
    </dct:creator>
    <dct:title>ESPnet2 pretrained model, Chenda Li/wsj0_2mix_enh_train_enh_conv_tasnet_raw_valid.si_snr.ave, fs=8k, lang=en</dct:title>
    <dct:publisher>
      <foaf:Agent>
        <foaf:name>Zenodo</foaf:name>
      </foaf:Agent>
    </dct:publisher>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#gYear">2021</dct:issued>
    <dcat:keyword>ESPnet</dcat:keyword>
    <dcat:keyword>deep-learning</dcat:keyword>
    <dcat:keyword>python</dcat:keyword>
    <dcat:keyword>pytorch</dcat:keyword>
    <dcat:keyword>speech-separation</dcat:keyword>
    <dcat:keyword>speech-recognition</dcat:keyword>
    <dcat:keyword>speech-synthesis</dcat:keyword>
    <dcat:keyword>speech-translation</dcat:keyword>
    <dcat:keyword>machine-translation</dcat:keyword>
    <dct:issued rdf:datatype="http://www.w3.org/2001/XMLSchema#date">2021-02-04</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/4498562"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/4498562</skos:notation>
        <adms:schemeAgency>url</adms:schemeAgency>
      </adms:Identifier>
    </adms:identifier>
    <dct:relation rdf:resource="https://github.com/espnet/espnet"/>
    <dct:isVersionOf rdf:resource="https://doi.org/10.5281/zenodo.4498561"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/espnet"/>
    <dct:description>&lt;p&gt;This model was trained by Chenda Li using wsj0_2mix recipe in &lt;a href="https://github.com/espnet/espnet/"&gt;espnet&lt;/a&gt;.&lt;/p&gt; &lt;p&gt;&amp;nbsp;&lt;/p&gt; &lt;ul&gt; &lt;li&gt;&lt;strong&gt;Python API&lt;/strong&gt; &lt;pre&gt;&lt;code class="language-python"&gt;See https://github.com/espnet/espnet_model_zoo&lt;/code&gt;&lt;/pre&gt; &lt;/li&gt; &lt;li&gt;&lt;strong&gt;Evaluate in the recipe&lt;/strong&gt; &lt;pre&gt;&lt;code class="language-bash"&gt;git clone https://github.com/espnet/espnet cd espnet git checkout a3334220b0352931677946d178fade3313cf82bb pip install -e . cd egs2/wsj0_2mix/enh1 ./run.sh --skip_data_prep false --skip_train true --download_model Chenda Li/wsj0_2mix_enh_train_enh_conv_tasnet_raw_valid.si_snr.ave&lt;/code&gt; &lt;/pre&gt; &lt;/li&gt; &lt;li&gt;&lt;strong&gt;Results&lt;/strong&gt; &lt;pre&gt;&lt;code&gt; # RESULTS ## Environments - date: `Thu Feb 4 01:16:18 CST 2021` - python version: `3.7.6 (default, Jan 8 2020, 19:59:22) [GCC 7.3.0]` - espnet version: `espnet 0.9.7` - pytorch version: `pytorch 1.5.0` - Git hash: `a3334220b0352931677946d178fade3313cf82bb` - Commit date: `Fri Jan 29 23:35:47 2021 +0800` ## enh_train_enh_conv_tasnet_raw config: ./conf/tuning/train_enh_conv_tasnet.yaml |dataset|STOI|SAR|SDR|SIR| |---|---|---|---|---| |enhanced_cv_min_8k|0.949205|17.3785|16.8028|26.9785| |enhanced_tt_min_8k|0.95349|16.6221|15.9494|25.9032|&lt;/code&gt;&lt;/pre&gt; &lt;/li&gt; &lt;li&gt;&lt;strong&gt;ASR config&lt;/strong&gt; &lt;pre&gt;&lt;code&gt;config: ./conf/tuning/train_enh_conv_tasnet.yaml print_config: false log_level: INFO dry_run: false iterator_type: chunk output_dir: exp/enh_train_enh_conv_tasnet_raw ngpu: 1 seed: 0 num_workers: 4 num_att_plot: 3 dist_backend: nccl dist_init_method: env:// dist_world_size: null dist_rank: null local_rank: 0 dist_master_addr: null dist_master_port: null dist_launcher: null multiprocessing_distributed: false cudnn_enabled: true cudnn_benchmark: false cudnn_deterministic: true collect_stats: false write_collected_feats: false max_epoch: 100 patience: 4 val_scheduler_criterion: - valid - loss early_stopping_criterion: - valid - loss - min best_model_criterion: - - valid - si_snr - max - - valid - loss - min keep_nbest_models: 1 grad_clip: 5.0 grad_clip_type: 2.0 grad_noise: false accum_grad: 1 no_forward_run: false resume: true train_dtype: float32 use_amp: false log_interval: null unused_parameters: false use_tensorboard: true use_wandb: false wandb_project: null wandb_id: null pretrain_path: null init_param: [] freeze_param: [] num_iters_per_epoch: null batch_size: 8 valid_batch_size: null batch_bins: 1000000 valid_batch_bins: null train_shape_file: - exp/enh_stats_8k/train/speech_mix_shape - exp/enh_stats_8k/train/speech_ref1_shape - exp/enh_stats_8k/train/speech_ref2_shape valid_shape_file: - exp/enh_stats_8k/valid/speech_mix_shape - exp/enh_stats_8k/valid/speech_ref1_shape - exp/enh_stats_8k/valid/speech_ref2_shape batch_type: folded valid_batch_type: null fold_length: - 80000 - 80000 - 80000 sort_in_batch: descending sort_batch: descending multiple_iterator: false chunk_length: 32000 chunk_shift_ratio: 0.5 num_cache_chunks: 1024 train_data_path_and_name_and_type: - - dump/raw/tr_min_8k/wav.scp - speech_mix - sound - - dump/raw/tr_min_8k/spk1.scp - speech_ref1 - sound - - dump/raw/tr_min_8k/spk2.scp - speech_ref2 - sound valid_data_path_and_name_and_type: - - dump/raw/cv_min_8k/wav.scp - speech_mix - sound - - dump/raw/cv_min_8k/spk1.scp - speech_ref1 - sound - - dump/raw/cv_min_8k/spk2.scp - speech_ref2 - sound allow_variable_data_keys: false max_cache_size: 0.0 max_cache_fd: 32 valid_max_cache_size: null optim: adam optim_conf: lr: 0.001 eps: 1.0e-08 weight_decay: 0 scheduler: reducelronplateau scheduler_conf: mode: min factor: 0.5 patience: 1 init: xavier_uniform model_conf: loss_type: si_snr use_preprocessor: false encoder: conv encoder_conf: channel: 256 kernel_size: 20 stride: 10 separator: tcn separator_conf: num_spk: 2 layer: 8 stack: 4 bottleneck_dim: 256 hidden_dim: 512 kernel: 3 causal: false norm_type: gLN nonlinear: relu decoder: conv decoder_conf: channel: 256 kernel_size: 20 stride: 10 required: - output_dir version: 0.9.7 distributed: false&lt;/code&gt;&lt;/pre&gt; &lt;/li&gt; &lt;/ul&gt;</dct:description>
    <dct:accessRights rdf:resource="http://publications.europa.eu/resource/authority/access-right/PUBLIC"/>
    <dct:accessRights>
      <dct:RightsStatement rdf:about="info:eu-repo/semantics/openAccess">
        <rdfs:label>Open Access</rdfs:label>
      </dct:RightsStatement>
    </dct:accessRights>
    <dct:license rdf:resource="https://creativecommons.org/licenses/by/4.0/legalcode"/>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.4498562"/>
        <dcat:byteSize>35240744</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/4498562/files/enh_train_enh_conv_tasnet_raw_valid.si_snr.ave.zip"/>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>