add all exp files

data/token_list/bpe_unigram150/bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0d67432adee6143fd0c0122606ee8b32712a544976bfbc159feeec2e7840193
+size 239511

exp/asr_train_asr_s3prl_single_lr1e-3_raw_en_bpe150_sp/RESULTS.md

@@ -0,0 +1,35 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Tue Mar  4 22:56:38 EST 2025`
+- python version: `3.9.21 (main, Dec 11 2024, 16:24:11)  [GCC 11.2.0]`
+- espnet version: `espnet 202412`
+- pytorch version: `pytorch 2.2.0+cu121`
+- Git hash: `b57dd0418ab2f7a03a21239f70decb9837cb2b0f`
+  - Commit date: `Wed Feb 5 07:19:24 2025 -0500`
+
+## exp_new/asr_train_asr_s3prl_single_lr1e-3_raw_en_bpe150_sp/decode_asr_ctc_lm_lm_train_lm_en_bpe150_valid.loss.ave_asr_model_valid.loss.ave
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|test/Hidalgo|324|3760|9.9|57.4|32.7|8.0|98.1|100.0|
+|test/Tequila|870|9337|14.0|62.5|23.4|8.8|94.8|100.0|
+|test/Zacatlan|1836|16318|21.9|56.6|21.5|5.1|83.2|99.6|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|test/Hidalgo|324|23998|62.4|13.0|24.6|15.3|52.9|100.0|
+|test/Tequila|870|65418|70.4|11.6|18.0|14.2|43.8|100.0|
+|test/Zacatlan|1836|108155|79.9|7.6|12.5|9.4|29.5|99.6|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|test/Hidalgo|324|13202|48.2|27.2|24.6|15.9|67.7|100.0|
+|test/Tequila|870|37224|55.5|25.3|19.3|13.8|58.3|100.0|
+|test/Zacatlan|1836|61871|66.2|19.4|14.4|8.4|42.2|99.6|
+

exp/asr_train_asr_s3prl_single_lr1e-3_raw_en_bpe150_sp/config.yaml

@@ -0,0 +1,364 @@
+config: conf/train_asr_s3prl_single_lr1e-3.yaml
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: sequence
+valid_iterator_type: null
+output_dir: exp_new/asr_train_asr_s3prl_single_lr1e-3_raw_en_bpe150_sp
+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
+unused_parameters: true
+sharded_ddp: false
+use_deepspeed: false
+deepspeed_config: null
+gradient_as_bucket_view: true
+ddp_comm_hook: null
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+use_tf32: false
+collect_stats: false
+write_collected_feats: false
+max_epoch: 15
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - loss
+    - min
+keep_nbest_models: 5
+nbest_averaging_interval: 0
+grad_clip: 5.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 4
+no_forward_run: false
+resume: true
+train_dtype: float32
+use_amp: false
+log_interval: null
+use_matplotlib: true
+use_tensorboard: true
+create_graph_in_tensorboard: false
+use_wandb: false
+wandb_project: null
+wandb_id: null
+wandb_entity: null
+wandb_name: null
+wandb_model_log_interval: -1
+detect_anomaly: false
+use_adapter: false
+adapter: lora
+save_strategy: all
+adapter_conf: {}
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param:
+- frontend.upstream
+num_iters_per_epoch: 500
+batch_size: 8
+valid_batch_size: null
+batch_bins: 1000000
+valid_batch_bins: null
+category_sample_size: 10
+train_shape_file:
+- exp_new/asr_stats_raw_en_bpe150_sp/train/speech_shape
+- exp_new/asr_stats_raw_en_bpe150_sp/train/text_shape.bpe
+valid_shape_file:
+- exp_new/asr_stats_raw_en_bpe150_sp/valid/speech_shape
+- exp_new/asr_stats_raw_en_bpe150_sp/valid/text_shape.bpe
+batch_type: sorted
+valid_batch_type: null
+fold_length:
+- 80000
+- 150
+sort_in_batch: descending
+shuffle_within_batch: false
+sort_batch: descending
+multiple_iterator: false
+chunk_length: 500
+chunk_shift_ratio: 0.5
+num_cache_chunks: 1024
+chunk_excluded_key_prefixes: []
+chunk_default_fs: null
+chunk_max_abs_length: null
+chunk_discard_short_samples: true
+train_data_path_and_name_and_type:
+-   - dump/raw/train_sp/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train_sp/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/dev/wav.scp
+    - speech
+    - sound
+-   - dump/raw/dev/text
+    - text
+    - text
+multi_task_dataset: false
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+allow_multi_rates: false
+valid_max_cache_size: null
+exclude_weight_decay: false
+exclude_weight_decay_conf: {}
+optim: adam
+optim_conf:
+    lr: 0.001
+    weight_decay: 1.0e-06
+scheduler: null
+scheduler_conf: {}
+token_list:
+- <blank>
+- <unk>
+- ':'
+- N
+- H
+- ▁
+- K
+- A
+- KA
+- ▁O
+- WA
+- ▁I
+- KI
+- S
+- TI
+- ▁A
+- MO
+- L
+- MA
+- TLA
+- NI
+- O
+- ▁KI
+- ▁N
+- WI
+- CHI
+- PA
+- ▁NO
+- CH
+- KO
+- X
+- ▁SE
+- LI
+- TO
+- ▁TLA
+- ▁WA
+- TL
+- I
+- TSI
+- TA
+- E
+- ▁NE
+- MI
+- ▁KE
+- 'NO'
+- TE
+- ▁NI
+- YA
+- ▁KA
+- ▁MA
+- ▁TI
+- NE
+- ''''
+- C
+- ▁MO
+- NA
+- KEH
+- ▁POS
+- ▁YA
+- ▁TLE
+- LA
+- ▁YO
+- PO
+- T
+- R
+- U
+- LIA
+- ▁TE
+- W
+- ▁KEH
+- ▁TO
+- TS
+- ▁YEH
+- MEH
+- ▁NEH
+- TOK
+- ▁OMPA
+- YO
+- SI
+- PI
+- ▁NIKA
+- LO
+- KE
+- B
+- D
+- LE
+- PE
+- XA
+- XI
+- ▁KO
+- M
+- SE
+- ME
+- ▁MM
+- ▁PERO
+- ▁OHKÓ
+- ▁NIK
+- ▁SI
+- MPA
+- Í
+- WE
+- ▁SAN
+- ▁TOS
+- ▁TIK
+- TLE
+- ▁NIKI
+- YI
+- ▁PARA
+- ▁PA
+- WEH
+- ▁DE
+- ▁NOCHI
+- TLI
+- P
+- TSO
+- HKEH
+- ▁SA
+- ▁TIKI
+- ▁E
+- RO
+- TSA
+- ▁IHKÓ
+- ▁B
+- ▁KWA
+- PIA
+- SO
+- Á
+- RA
+- V
+- ▁YE
+- ▁YEHWA
+- ▁AHÁ
+- YE
+- Z
+- J
+- Ó
+- G
+- É
+- Y
+- '-'
+- ̈
+- ¡
+- Ú
+- Ñ
+- F
+- Q
+- Ü
+- ¿
+- Ï
+- <sos/eos>
+init: null
+input_size: null
+ctc_conf:
+    dropout_rate: 0.0
+    ctc_type: builtin
+    reduce: true
+    ignore_nan_grad: null
+    zero_infinity: true
+    brctc_risk_strategy: exp
+    brctc_group_strategy: end
+    brctc_risk_factor: 0.0
+joint_net_conf: null
+use_preprocessor: true
+use_lang_prompt: false
+use_nlp_prompt: false
+token_type: bpe
+bpemodel: data/en_token_list/bpe_unigram150/bpe.model
+non_linguistic_symbols: null
+cleaner: null
+g2p: null
+speech_volume_normalize: null
+rir_scp: null
+rir_apply_prob: 1.0
+noise_scp: null
+noise_apply_prob: 1.0
+noise_db_range: '13_15'
+short_noise_thres: 0.5
+aux_ctc_tasks: []
+frontend: s3prl
+frontend_conf:
+    frontend_conf:
+        upstream: hubert_large_ll60k
+    download_dir: ./hub
+    multilayer_feature: true
+    fs: 16k
+specaug: specaug
+specaug_conf:
+    apply_time_warp: true
+    time_warp_window: 5
+    time_warp_mode: bicubic
+    apply_freq_mask: true
+    freq_mask_width_range:
+    - 0
+    - 27
+    num_freq_mask: 2
+    apply_time_mask: true
+    time_mask_width_ratio_range:
+    - 0.0
+    - 0.05
+    num_time_mask: 10
+normalize: utterance_mvn
+normalize_conf: {}
+model: espnet
+model_conf:
+    ctc_weight: 1.0
+preencoder: linear
+preencoder_conf:
+    input_size: 1024
+    output_size: 80
+encoder: transformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 8
+    linear_units: 1024
+    num_blocks: 2
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d2
+    normalize_before: true
+postencoder: null
+postencoder_conf: {}
+decoder: null
+decoder_conf: {}
+preprocessor: default
+preprocessor_conf: {}
+required:
+- output_dir
+- token_list
+version: '202412'
+distributed: false

exp/asr_train_asr_s3prl_single_lr1e-3_raw_en_bpe150_sp/valid.loss.ave_5best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31d5303f7c423f1e870dd74a6d4b09a13d70e0acf3f7863035226934eabaef3e
+size 1285514315