January 12, 2021 Other Open Access

kan-bayashi

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.4433196">
    <dct:identifier rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://doi.org/10.5281/zenodo.4433196</dct:identifier>
    <foaf:page rdf:resource="https://doi.org/10.5281/zenodo.4433196"/>
    <dct:creator>
      <rdf:Description>
        <rdf:type rdf:resource="http://xmlns.com/foaf/0.1/Agent"/>
        <foaf:name>kan-bayashi</foaf:name>
      </rdf:Description>
    </dct:creator>
    <dct:title>ESPnet2 pretrained model, kan-bayashi/jsut_tts_train_transformer_raw_phn_jaconv_pyopenjtalk_accent_with_pause_train.loss.ave, fs=24000, lang=jp</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-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">2021-01-12</dct:issued>
    <owl:sameAs rdf:resource="https://zenodo.org/record/4433196"/>
    <adms:identifier>
      <adms:Identifier>
        <skos:notation rdf:datatype="http://www.w3.org/2001/XMLSchema#anyURI">https://zenodo.org/record/4433196</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.4433195"/>
    <dct:isPartOf rdf:resource="https://zenodo.org/communities/espnet"/>
    <dct:description>&lt;p&gt;This model was trained by kan-bayashi using jsut/tts1 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 18fb6edb7b14911730337baa05f0e40c4dde9002 pip install -e . cd egs2/jsut/tts1 # Download the model file here ./run.sh --skip_data_prep false --skip_train true --download_model kan-bayashi/jsut_tts_train_transformer_raw_phn_jaconv_pyopenjtalk_accent_with_pause_train.loss.ave&lt;/code&gt; &lt;/pre&gt; &lt;/li&gt; &lt;li&gt;&lt;strong&gt;Config&lt;/strong&gt; &lt;pre&gt;&lt;code&gt;config: conf/tuning/train_transformer.yaml print_config: false log_level: INFO dry_run: false iterator_type: sequence output_dir: exp/tts_train_transformer_raw_phn_jaconv_pyopenjtalk_accent_with_pause ngpu: 1 seed: 0 num_workers: 1 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: 58625 dist_launcher: null multiprocessing_distributed: true cudnn_enabled: true cudnn_benchmark: false cudnn_deterministic: true collect_stats: false write_collected_feats: false max_epoch: 200 patience: null val_scheduler_criterion: - valid - loss early_stopping_criterion: - valid - loss - min best_model_criterion: - - valid - loss - min - - train - loss - min keep_nbest_models: 5 grad_clip: 1.0 grad_clip_type: 2.0 grad_noise: false accum_grad: 2 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: 1000 batch_size: 20 valid_batch_size: null batch_bins: 9000000 valid_batch_bins: null train_shape_file: - exp/tts_stats_raw_phn_jaconv_pyopenjtalk_accent_with_pause/train/text_shape.phn - exp/tts_stats_raw_phn_jaconv_pyopenjtalk_accent_with_pause/train/speech_shape valid_shape_file: - exp/tts_stats_raw_phn_jaconv_pyopenjtalk_accent_with_pause/valid/text_shape.phn - exp/tts_stats_raw_phn_jaconv_pyopenjtalk_accent_with_pause/valid/speech_shape batch_type: numel valid_batch_type: null fold_length: - 150 - 240000 sort_in_batch: descending sort_batch: descending multiple_iterator: false chunk_length: 500 chunk_shift_ratio: 0.5 num_cache_chunks: 1024 train_data_path_and_name_and_type: - - dump/raw/tr_no_dev/text - text - text - - dump/raw/tr_no_dev/wav.scp - speech - sound valid_data_path_and_name_and_type: - - dump/raw/dev/text - text - text - - dump/raw/dev/wav.scp - speech - 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: 1.0 scheduler: noamlr scheduler_conf: model_size: 512 warmup_steps: 8000 token_list: - - - '1' - '2' - '0' - '3' - '4' - '-1' - '5' - a - o - '-2' - i - '-3' - u - e - k - n - t - '6' - r - '-4' - s - N - m - pau - '7' - sh - d - g - w - '8' - U - '-5' - I - cl - h - y - b - '9' - j - ts - ch - '-6' - z - p - '-7' - f - ky - ry - '-8' - gy - '-9' - hy - ny - '-10' - by - my - '-11' - '-12' - '-13' - py - '-14' - '-15' - v - '10' - '-16' - '-17' - '11' - '-21' - '-20' - '12' - '-19' - '13' - '-18' - '14' - dy - '15' - ty - '-22' - '16' - '18' - '19' - '17' - odim: null model_conf: {} use_preprocessor: true token_type: phn bpemodel: null non_linguistic_symbols: null cleaner: jaconv g2p: pyopenjtalk_accent_with_pause feats_extract: fbank feats_extract_conf: fs: 24000 fmin: 80 fmax: 7600 n_mels: 80 hop_length: 300 n_fft: 2048 win_length: 1200 normalize: global_mvn normalize_conf: stats_file: exp/tts_stats_raw_phn_jaconv_pyopenjtalk_accent_with_pause/train/feats_stats.npz tts: transformer tts_conf: embed_dim: 0 eprenet_conv_layers: 0 eprenet_conv_filts: 0 eprenet_conv_chans: 0 dprenet_layers: 2 dprenet_units: 256 adim: 512 aheads: 8 elayers: 6 eunits: 1024 dlayers: 6 dunits: 1024 positionwise_layer_type: conv1d positionwise_conv_kernel_size: 1 postnet_layers: 5 postnet_filts: 5 postnet_chans: 256 use_masking: true bce_pos_weight: 5.0 use_scaled_pos_enc: true encoder_normalize_before: true decoder_normalize_before: true reduction_factor: 1 init_type: xavier_uniform init_enc_alpha: 1.0 init_dec_alpha: 1.0 eprenet_dropout_rate: 0.0 dprenet_dropout_rate: 0.5 postnet_dropout_rate: 0.5 transformer_enc_dropout_rate: 0.1 transformer_enc_positional_dropout_rate: 0.1 transformer_enc_attn_dropout_rate: 0.1 transformer_dec_dropout_rate: 0.1 transformer_dec_positional_dropout_rate: 0.1 transformer_dec_attn_dropout_rate: 0.1 transformer_enc_dec_attn_dropout_rate: 0.1 use_guided_attn_loss: true num_heads_applied_guided_attn: 2 num_layers_applied_guided_attn: 2 modules_applied_guided_attn: - encoder-decoder guided_attn_loss_sigma: 0.4 guided_attn_loss_lambda: 10.0 pitch_extract: null pitch_extract_conf: {} pitch_normalize: null pitch_normalize_conf: {} energy_extract: null energy_extract_conf: {} energy_normalize: null energy_normalize_conf: {} required: - output_dir - token_list distributed: true&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-nc-sa/4.0/legalcode"/>
    <dcat:distribution>
      <dcat:Distribution>
        <dcat:accessURL rdf:resource="https://doi.org/10.5281/zenodo.4433196"/>
        <dcat:byteSize>133238771</dcat:byteSize>
        <dcat:downloadURL rdf:resource="https://zenodo.org/record/4433196/files/tts_train_transformer_raw_phn_jaconv_pyopenjtalk_accent_with_pause_train.loss.ave.zip"/>
        <dcat:mediaType>application/zip</dcat:mediaType>
      </dcat:Distribution>
    </dcat:distribution>
  </rdf:Description>
</rdf:RDF>