add pretrained model

exp/asr_train_asr_transformer_raw_char_1gpu/RESULTS.md

@@ -0,0 +1,10 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Tue Sep  1 15:32:18 CST 2020`
+- python version: `3.7.6 (default, Jan  8 2020, 19:59:22)  [GCC 7.3.0]`
+- espnet version: `espnet 0.9.0`
+- pytorch version: `pytorch 1.5.0`
+- Git hash: `9e8a87e02872a9a5e8f58cb0521eda05058195ca`
+  - Commit date: `Mon Aug 24 20:21:25 2020 +0800`
+

exp/asr_train_asr_transformer_raw_char_1gpu/config.yaml

@@ -0,0 +1,208 @@
+config: conf/train_asr_transformer.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: ./exp/asr_train_asr_transformer_raw_char_1gpu
+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: 100
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - acc
+    - max
+keep_nbest_models: 10
+grad_clip: 5.0
+grad_noise: false
+accum_grad: 8
+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: 1000000
+valid_batch_bins: null
+train_shape_file:
+- exp/asr_stats_raw/train/speech_shape
+- exp/asr_stats_raw/train/text_shape.char
+valid_shape_file:
+- exp/asr_stats_raw/valid/speech_shape
+- exp/asr_stats_raw/valid/text_shape.char
+batch_type: folded
+valid_batch_type: null
+fold_length:
+- 80000
+- 150
+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_si284/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train_si284/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/test_dev93/wav.scp
+    - speech
+    - sound
+-   - dump/raw/test_dev93/text
+    - text
+    - text
+allow_variable_data_keys: false
+max_cache_size: 0.0
+valid_max_cache_size: null
+optim: adam
+optim_conf:
+    lr: 0.005
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 30000
+token_list:
+- <blank>
+- <unk>
+- <space>
+- E
+- T
+- A
+- N
+- I
+- O
+- S
+- R
+- H
+- L
+- D
+- C
+- U
+- M
+- P
+- F
+- G
+- Y
+- W
+- B
+- V
+- K
+- .
+- X
+- ''''
+- J
+- Q
+- Z
+- <NOISE>
+- ','
+- '-'
+- '"'
+- '*'
+- ':'
+- (
+- )
+- '?'
+- '!'
+- '&'
+- ;
+- '1'
+- '2'
+- '0'
+- /
+- $
+- '{'
+- '}'
+- '8'
+- '9'
+- '6'
+- '3'
+- '5'
+- '7'
+- '4'
+- '~'
+- '`'
+- _
+- <*IN*>
+- <*MR.*>
+- \
+- ^
+- <sos/eos>
+init: xavier_uniform
+input_size: null
+ctc_conf:
+    dropout_rate: 0.0
+    ctc_type: builtin
+    reduce: true
+model_conf:
+    ctc_weight: 0.3
+    lsm_weight: 0.1
+    length_normalized_loss: false
+use_preprocessor: true
+token_type: char
+bpemodel: null
+non_linguistic_symbols: data/nlsyms.txt
+cleaner: null
+g2p: null
+frontend: default
+frontend_conf:
+    fs: 8k
+    n_fft: 256
+    hop_length: 64
+specaug: null
+specaug_conf: {}
+normalize: global_mvn
+normalize_conf:
+    stats_file: exp/asr_stats_raw/train/feats_stats.npz
+encoder: transformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 4
+    linear_units: 2048
+    num_blocks: 12
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.0
+    input_layer: conv2d
+    normalize_before: true
+decoder: transformer
+decoder_conf:
+    attention_heads: 4
+    linear_units: 2048
+    num_blocks: 6
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    self_attention_dropout_rate: 0.0
+    src_attention_dropout_rate: 0.0
+required:
+- output_dir
+- token_list
+distributed: false

exp/asr_train_asr_transformer_raw_char_1gpu/valid.acc.ave_10best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88b898a6f90867382bba18481feb0dc497e33a88c6ef2ebe3f7816f131a2d9be
+size 108690752

exp/lm_train_lm_char_sgd/37epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59fb8554c7a96c1c2ed30eee5eb30b9797659d767af739c27526c9159bf4964d
+size 27421563

exp/lm_train_lm_char_sgd/config.yaml

@@ -0,0 +1,165 @@
+config: conf/train_lm.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: ./exp/lm_train_lm_char_sgd
+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: 40
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 1
+grad_clip: 5.0
+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: 30
+valid_batch_size: null
+batch_bins: 1000000
+valid_batch_bins: null
+train_shape_file:
+- exp/lm_stats/train/text_shape.char
+valid_shape_file:
+- exp/lm_stats/valid/text_shape.char
+batch_type: folded
+valid_batch_type: null
+fold_length:
+- 150
+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/srctexts
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/test_dev93/text
+    - text
+    - text
+allow_variable_data_keys: false
+max_cache_size: 0.0
+valid_max_cache_size: null
+optim: sgd
+optim_conf:
+    lr: 0.1
+scheduler: null
+scheduler_conf: {}
+token_list:
+- <blank>
+- <unk>
+- <space>
+- E
+- T
+- A
+- N
+- I
+- O
+- S
+- R
+- H
+- L
+- D
+- C
+- U
+- M
+- P
+- F
+- G
+- Y
+- W
+- B
+- V
+- K
+- .
+- X
+- ''''
+- J
+- Q
+- Z
+- <NOISE>
+- ','
+- '-'
+- '"'
+- '*'
+- ':'
+- (
+- )
+- '?'
+- '!'
+- '&'
+- ;
+- '1'
+- '2'
+- '0'
+- /
+- $
+- '{'
+- '}'
+- '8'
+- '9'
+- '6'
+- '3'
+- '5'
+- '7'
+- '4'
+- '~'
+- '`'
+- _
+- <*IN*>
+- <*MR.*>
+- \
+- ^
+- <sos/eos>
+init: null
+model_conf:
+    ignore_id: 0
+use_preprocessor: true
+token_type: char
+bpemodel: null
+non_linguistic_symbols: data/nlsyms.txt
+cleaner: null
+g2p: null
+lm: seq_rnn
+lm_conf:
+    unit: 650
+    nlayers: 2
+required:
+- output_dir
+- token_list
+distributed: false

exp/lm_train_lm_char_sgd/perplexity_test/ppl

@@ -0,0 +1 @@
+2.4762186648823223

meta.yaml

@@ -0,0 +1,10 @@
+espnet: 0.9.0
+files:
+  asr_model_file: exp/asr_train_asr_transformer_raw_char_1gpu/valid.acc.ave_10best.pth
+  lm_file: exp/lm_train_lm_char_sgd/37epoch.pth
+python: "3.7.6 (default, Jan  8 2020, 19:59:22) \n[GCC 7.3.0]"
+timestamp: 1599059847.47611
+torch: 1.5.0
+yaml_files:
+  asr_train_config: exp/asr_train_asr_transformer_raw_char_1gpu/config.yaml
+  lm_train_config: exp/lm_train_lm_char_sgd/config.yaml