add model files

README.md

@@ -0,0 +1,9 @@
+---
+tags:
+- espnet
+- audio
+- text-to-speech
+language: gos
+---
+
+# Tacotron2 Gronings

exp/tts_ljspeech_finetune_tacotron2.v5/config.yaml

@@ -0,0 +1,230 @@
+config: conf/tuning/finetune_tacotron2.v5.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/tts_ljspeech_finetune_tacotron2.v5
+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
+unused_parameters: false
+sharded_ddp: false
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+collect_stats: false
+write_collected_feats: false
+max_epoch: 50
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - attn_loss
+    - min
+-   - train
+    - loss
+    - min
+keep_nbest_models: 5
+grad_clip: 1.0
+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
+use_tensorboard: true
+use_wandb: true
+wandb_project: null
+wandb_id: null
+pretrain_path: null
+init_param:
+- downloads/3b0a779f28d99232479e782d4d20292b/exp/tts_train_tacotron2_raw_phn_tacotron_g2p_en_no_space/199epoch.pth:::tts.enc.embed,normalize
+freeze_param: []
+num_iters_per_epoch: 500
+batch_size: 20
+valid_batch_size: null
+batch_bins: 3750000
+valid_batch_bins: null
+train_shape_file:
+- exp/tts_stats_raw_char/train/text_shape.char
+- exp/tts_stats_raw_char/train/speech_shape
+valid_shape_file:
+- exp/tts_stats_raw_char/valid/text_shape.char
+- exp/tts_stats_raw_char/valid/speech_shape
+batch_type: numel
+valid_batch_type: null
+fold_length:
+- 150
+- 204800
+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/train_nodev/text
+    - text
+    - text
+-   - dump/raw/train_nodev/wav.scp
+    - speech
+    - sound
+valid_data_path_and_name_and_type:
+-   - dump/raw/train_dev/text
+    - text
+    - text
+-   - dump/raw/train_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: 0.001
+    eps: 1.0e-06
+    weight_decay: 0.0
+scheduler: null
+scheduler_conf: {}
+token_list:
+- <blank>
+- <unk>
+- <space>
+- e
+- n
+- a
+- t
+- i
+- r
+- o
+- d
+- l
+- h
+- s
+- g
+- k
+- m
+- j
+- z
+- v
+- .
+- w
+- u
+- b
+- p
+- c
+- ''''
+- f
+- ','
+- '?'
+- y
+- é
+- ':'
+- x
+- '-'
+- ë
+- '!'
+- q
+- '"'
+- á
+- ï
+- è
+- ó
+- í
+- ;
+- '&'
+- )
+- (
+- ü
+- ö
+- ê
+- ú
+- /
+- ä
+- à
+- <sos/eos>
+odim: null
+model_conf: {}
+use_preprocessor: true
+token_type: char
+bpemodel: null
+non_linguistic_symbols: null
+cleaner: null
+g2p: null
+feats_extract: fbank
+feats_extract_conf:
+    fs: 22050
+    fmin: 80
+    fmax: 7600
+    n_mels: 80
+    hop_length: 256
+    n_fft: 1024
+    win_length: null
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/tts_stats_raw_char/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: 2
+    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
+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
+version: 0.9.7
+distributed: false

exp/tts_ljspeech_finetune_tacotron2.v5/train.loss.ave_5best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b0e7cf1f3beae57ae5ee4429ab8e5bc002947bcad64d9c15dd4d7191d88bb6a
+size 107312986

meta.yaml

@@ -0,0 +1,9 @@
+espnet: 0.9.7
+files:
+  model_file: exp/tts_ljspeech_finetune_tacotron2.v5/train.loss.ave_5best.pth
+python: "3.8.8 | packaged by conda-forge | (default, Feb 20 2021, 16:22:27) \n[GCC\
+  \ 9.3.0]"
+timestamp: 1614414989.925269
+torch: 1.7.1
+yaml_files:
+  train_config: exp/tts_ljspeech_finetune_tacotron2.v5/config.yaml

tts_ljspeech_finetune_tacotron2.v5_train.loss.ave.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:65c4b51686bfcc1754f40e8570d1a48574f1c97ce5105cb90e9ec9a0cbc6464a
+size 107754064