initial import from https://zenodo.org/record/3969118

.gitattributes

@@ -6,3 +6,4 @@
 *.tar.gz filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text

exp/tts_train_tacotron2_raw_phn_pypinyin_g2p_phone/199epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10844464e4febdfeaae598b185b99ae6c46e2322f4ad93fcc63f20a13972a611
+size 107274977

exp/tts_train_tacotron2_raw_phn_pypinyin_g2p_phone/config.yaml

@@ -0,0 +1,361 @@
+config: conf/train.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/tts_train_raw_phn_pypinyin_g2p_phone
+ngpu: 1
+seed: 0
+num_workers: 1
+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: 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_noise: false
+accum_grad: 1
+no_forward_run: false
+resume: true
+train_dtype: float32
+log_interval: null
+pretrain_path: []
+pretrain_key: []
+num_iters_per_epoch: null
+batch_size: 20
+valid_batch_size: null
+batch_bins: 3750000
+valid_batch_bins: null
+train_shape_file:
+- exp/tts_stats_raw_phn_pypinyin_g2p_phone/train/text_shape.phn
+- exp/tts_stats_raw_phn_pypinyin_g2p_phone/train/speech_shape
+valid_shape_file:
+- exp/tts_stats_raw_phn_pypinyin_g2p_phone/valid/text_shape.phn
+- exp/tts_stats_raw_phn_pypinyin_g2p_phone/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
+valid_max_cache_size: null
+optim: adam
+optim_conf:
+    lr: 0.001
+    eps: 1.0e-06
+    weight_decay: 0.0
+scheduler: null
+scheduler_conf: {}
+token_list:
+- <blank>
+- <unk>
+- "\uFF30"
+- "\uFF22"
+- "\xFC"
+- an
+- ueng3
+- '2'
+- uen
+- ei
+- ua
+- ao
+- u
+- ueng4
+- uo
+- ang
+- ou
+- v2
+- ueng1
+- o
+- io1
+- "\xFCn3"
+- er
+- ve4
+- o3
+- uai2
+- uen3
+- uen1
+- uai3
+- "\xFCe3"
+- iou1
+- iong2
+- ia2
+- uai1
+- iong1
+- "\xFCan1"
+- "\xFCe1"
+- v4
+- ua3
+- ia
+- iong3
+- uei3
+- ua2
+- ia3
+- uei1
+- o1
+- o4
+- "\xFCn2"
+- un2
+- er3
+- "\xFCn1"
+- uen4
+- un3
+- iu1
+- "\xFCn4"
+- uen2
+- "\xFCan3"
+- un4
+- "\xFCan4"
+- iu3
+- ua1
+- uei2
+- "\uFF01"
+- iou4
+- iou2
+- er4
+- o2
+- ei1
+- iao2
+- uang4
+- "\xFC1"
+- ui2
+- v3
+- uang2
+- iong4
+- un1
+- ui1
+- ua4
+- ao2
+- en
+- a
+- iu2
+- uang1
+- uang3
+- "\xFCe2"
+- in3
+- "\uFF1F"
+- uai4
+- "\xFCe4"
+- uan2
+- ou2
+- eng3
+- ui3
+- uan4
+- a2
+- ie2
+- ong3
+- iang2
+- ie1
+- in4
+- iao1
+- e1
+- in2
+- en4
+- uan3
+- "\xFC2"
+- ing3
+- i
+- ei2
+- ei3
+- iang1
+- er2
+- ia4
+- uo2
+- "\xFC3"
+- uan1
+- ia1
+- e3
+- ong4
+- ie4
+- ai1
+- en3
+- iang3
+- eng4
+- iang4
+- ao1
+- ou1
+- ang2
+- ai3
+- iu4
+- "\xFCan2"
+- ang3
+- en1
+- ong2
+- uei4
+- ei4
+- iao3
+- "\xFC4"
+- an2
+- ing4
+- an3
+- a3
+- ie3
+- an1
+- ian3
+- uo1
+- ing1
+- ou4
+- ian1
+- ou3
+- eng1
+- ang1
+- in1
+- a4
+- eng2
+- uo4
+- u1
+- ang4
+- iou3
+- iao4
+- ian2
+- u2
+- ui4
+- e2
+- en2
+- u3
+- ing2
+- ao4
+- ong1
+- an4
+- ai2
+- ao3
+- uo3
+- ian4
+- p
+- c
+- a1
+- ai4
+- e4
+- s
+- k
+- r
+- i2
+- f
+- n
+- u4
+- ch
+- i3
+- i1
+- q
+- z
+- m
+- t
+- g
+- b
+- e
+- h
+- i4
+- x
+- "\uFF0C"
+- zh
+- "\u3002"
+- l
+- j
+- sh
+- d
+- <sos/eos>
+odim: null
+model_conf: {}
+use_preprocessor: true
+token_type: phn
+bpemodel: null
+non_linguistic_symbols: null
+cleaner: null
+g2p: pypinyin_g2p_phone
+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_pypinyin_g2p_phone/train/feats_stats.npz
+tts: tacotron2
+tts_conf:
+    embed_dim: 512
+    elayers: 1
+    eunits: 512
+    econv_layers: 3
+    econv_chans: 512
+    econv_filts: 5
+    atype: location
+    adim: 512
+    aconv_chans: 32
+    aconv_filts: 15
+    cumulate_att_w: true
+    dlayers: 2
+    dunits: 1024
+    prenet_layers: 2
+    prenet_units: 256
+    postnet_layers: 5
+    postnet_chans: 512
+    postnet_filts: 5
+    output_activation: null
+    use_batch_norm: true
+    use_concate: true
+    use_residual: false
+    dropout_rate: 0.5
+    zoneout_rate: 0.1
+    reduction_factor: 1
+    spk_embed_dim: null
+    use_masking: true
+    bce_pos_weight: 5.0
+    use_guided_attn_loss: true
+    guided_attn_loss_sigma: 0.4
+    guided_attn_loss_lambda: 1.0
+required:
+- output_dir
+- token_list
+distributed: false

meta.yaml

@@ -0,0 +1,8 @@
+espnet: 0.8.0
+files:
+  model_file: exp/tts_train_tacotron2_raw_phn_pypinyin_g2p_phone/199epoch.pth
+python: "3.7.3 (default, Mar 27 2019, 22:11:17) \n[GCC 7.3.0]"
+timestamp: 1596252269.687669
+torch: 1.5.1
+yaml_files:
+  train_config: exp/tts_train_tacotron2_raw_phn_pypinyin_g2p_phone/config.yaml