ESPnet2 pretrained model, kamo-naoyuki/librispeech_asr_train_asr_conformer6_n_fft512_hop_length256_raw_en_bpe5000_scheduler_confwarmup_steps40000_optim_conflr0.0025_sp_valid.acc.ave, fs=16k, lang=en
kamo-naoyuki · Zenodo (CERN European Organization for Nuclear Research) · 2021
This model was trained by kamo-naoyuki using librispeech recipe in espnet. Python API See https://github.com/espnet/espnet_model_zoo Evaluate in the recipe git clone https://github.com/espnet/espnet cd espnet git checkout 2ccd176da5de478e115600b874952cebc549c6ef pip install -e . cd egs2/librispeech/asr1 ./run.sh --skip_data_prep false --skip_train true --download_model kamo-naoyuki/librispeech_asr_train_asr_conformer6_n_fft512_hop_length256_raw_en_bpe5000_scheduler_confwarmup_steps40000_optim_conflr0.0025_sp_valid.acc.ave Results # RESULTS ## Environments - date: `Thu Mar 11 15:30:44 UTC 2021` - python version: `3.8.8 (default, Feb 24 2021, 21:46:12) [GCC 7.3.0]` - espnet version: `espnet 0.9.8` - pytorch version: `pytorch 1.8.0` - Git hash: `2ccd176da5de478e115600b874952cebc549c6ef` - Commit date: `Mon Mar 8 10:41:31 2021 +0000` ## asr_train_asr_conformer6_n_fft512_hop_length256_raw_en_bpe5000_scheduler_confwarmup_steps40000_optim_conflr0.0025_sp ### WER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |decode_asr_asr_model_valid.acc.ave/dev_clean|2703|54402|97.9|1.9|0.2|0.2|2.3|28.6| |decode_asr_asr_model_valid.acc.ave/dev_other|2864|50948|94.5|5.1|0.5|0.6|6.1|48.3| |decode_asr_asr_model_valid.acc.ave/test_clean|2620|52576|97.7|2.1|0.2|0.3|2.6|31.4| |decode_asr_asr_model_valid.acc.ave/test_other|2939|52343|94.7|4.9|0.5|0.7|6.0|49.0| |decode_asr_lm_lm_train_lm_transformer2_bpe5000_scheduler_confwarmup_steps25000_batch_bins500000000_accum_grad2_use_amptrue_valid.loss.ave_asr_model_valid.acc.ave/dev_clean|2703|54402|98.3|1.5|0.2|0.2|1.9|25.2| |decode_asr_lm_lm_train_lm_transformer2_bpe5000_scheduler_confwarmup_steps25000_batch_bins500000000_accum_grad2_use_amptrue_valid.loss.ave_asr_model_valid.acc.ave/dev_other|2864|50948|95.8|3.7|0.4|0.5|4.6|40.0| |decode_asr_lm_lm_train_lm_transformer2_bpe5000_scheduler_confwarmup_steps25000_batch_bins500000000_accum_grad2_use_amptrue_valid.loss.ave_asr_model_valid.acc.ave/test_clean|2620|52576|98.1|1.7|0.2|0.3|2.1|26.2| |decode_asr_lm_lm_train_lm_transformer2_bpe5000_scheduler_confwarmup_steps25000_batch_bins500000000_accum_grad2_use_amptrue_valid.loss.ave_asr_model_valid.acc.ave/test_other|2939|52343|95.8|3.7|0.5|0.5|4.7|42.4| ### CER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |decode_asr_asr_model_valid.acc.ave/dev_clean|2703|288456|99.4|0.3|0.2|0.2|0.8|28.6| |decode_asr_asr_model_valid.acc.ave/dev_other|2864|265951|98.0|1.2|0.8|0.7|2.7|48.3| |decode_asr_asr_model_valid.acc.ave/test_clean|2620|281530|99.4|0.3|0.3|0.3|0.9|31.4| |decode_asr_asr_model_valid.acc.ave/test_other|2939|272758|98.2|1.0|0.7|0.7|2.5|49.0| |decode_asr_lm_lm_train_lm_transformer2_bpe5000_scheduler_confwarmup_steps25000_batch_bins500000000_accum_grad2_use_amptrue_valid.loss.ave_asr_model_valid.acc.ave/dev_clean|2703|288456|99.5|0.3|0.2|0.2|0.7|25.2| |decode_asr_lm_lm_train_lm_transformer2_bpe5000_scheduler_confwarmup_steps25000_batch_bins500000000_accum_grad2_use_amptrue_valid.loss.ave_asr_model_valid.acc.ave/dev_other|2864|265951|98.3|1.0|0.7|0.5|2.2|40.0| |decode_asr_lm_lm_train_lm_transformer2_bpe5000_scheduler_confwarmup_steps25000_batch_bins500000000_accum_grad2_use_amptrue_valid.loss.ave_asr_model_valid.acc.ave/test_clean|2620|281530|99.5|0.3|0.3|0.2|0.7|26.2| |decode_asr_lm_lm_train_lm_transformer2_bpe5000_scheduler_confwarmup_steps25000_batch_bins500000000_accum_grad2_use_amptrue_valid.loss.ave_asr_model_valid.acc.ave/test_other|2939|272758|98.5|0.8|0.7|0.5|2.1|42.4| ### TER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |decode_asr_asr_model_valid.acc.ave/dev_clean|2703|68010|97.5|1.9|0.7|0.4|2.9|28.6| |decode_asr_asr_model_valid.acc.ave/dev_other|2864|63110|93.4|5.0|1.6|1.0|7.6|48.3| |decode_asr_asr_model_valid.acc.ave/test_clean|2620|65818|97.2|2.0|0.8|0.4|3.3|31.4| |decode_asr_asr_model_valid.acc.ave/test_other|2939|65101|93.7|4.5|1.8|0.9|7.2|49.0| |decode_asr_lm_lm_train_lm_transformer2_bpe5000_scheduler_confwarmup_steps25000_batch_bins500000000_accum_grad2_use_amptrue_valid.loss.ave_asr_model_valid.acc.ave/dev_clean|2703|68010|97.8|1.5|0.7|0.3|2.5|25.2| |decode_asr_lm_lm_train_lm_transformer2_bpe5000_scheduler_confwarmup_steps25000_batch_bins500000000_accum_grad2_use_amptrue_valid.loss.ave_asr_model_valid.acc.ave/dev_other|2864|63110|94.6|3.8|1.6|0.7|6.1|40.0| |decode_asr_lm_lm_train_lm_transformer2_bpe5000_scheduler_confwarmup_steps25000_batch_bins500000000_accum_grad2_use_amptrue_valid.loss.ave_asr_model_valid.acc.ave/test_clean|2620|65818|97.6|1.6|0.8|0.3|2.7|26.2| |decode_asr_lm_lm_train_lm_transformer2_bpe5000_scheduler_confwarmup_steps25000_batch_bins500000000_accum_grad2_use_amptrue_valid.loss.ave_asr_model_valid.acc.ave/test_other|2939|65101|94.7|3.5|1.8|0.7|6.0|42.4| ASR config config: conf/tuning/train_asr_conformer6_n_fft512_hop_length256.yaml print_config: false log_level: INFO dry_run: false iterator_type: sequence output_dir: exp/asr_train_asr_conformer6_n_fft512_hop_length256_raw_en_bpe5000_scheduler_confwarmup_steps40000_optim_conflr0.0025_sp ngpu: 1 seed: 0 num_workers: 1 num_att_plot: 3 dist_backend: nccl dist_init_method: env:// dist_world_size: 8 dist_rank: 0 local_rank: 0 dist_master_addr: localhost dist_master_port: 33850 dist_launcher: null multiprocessing_distributed: true unused_parameters: false sharded_ddp: false cudnn_enabled: true cudnn_benchmark: false cudnn_deterministic: true collect_stats: false write_collected_feats: false max_epoch: 35 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_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: false wandb_project: null wandb_id: null detect_anomaly: false pretrain_path: null init_param: [] freeze_param: [] num_iters_per_epoch: null batch_size: 20 valid_batch_size: null batch_bins: 140000000 valid_batch_bins: null train_shape_file: - exp/asr_stats_raw_bpe5000_n_fft512_hop256_sp/train/speech_shape - exp/asr_stats_raw_bpe5000_n_fft512_hop256_sp/train/text_shape.bpe valid_shape_file: - exp/asr_stats_raw_bpe5000_n_fft512_hop256_sp/valid/speech_shape - exp/asr_stats_raw_bpe5000_n_fft512_hop256_sp/valid/text_shape.bpe batch_type: numel 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_960_sp/wav.scp - speech - kaldi_ark - - dump/raw/train_960_sp/text - text - text valid_data_path_and_name_and_type: - - dump/raw/dev/wav.scp - speech - kaldi_ark - - dump/raw/dev/text - text - text allow_variable_data_keys: false max_cache_size: 0.0 max_cache_fd: 32 valid_max_cache_size: null optim: adam optim_conf: lr: 0.0025 scheduler: warmuplr scheduler_conf: warmup_steps: 40000 token_list: - - - ▁THE - S - ▁AND - ▁OF - ▁TO - ▁A - ▁IN - ▁I - ▁HE - ▁THAT - ▁WAS - ED - ▁IT - '''' - ▁HIS - ING - ▁YOU - ▁WITH - ▁FOR - ▁HAD - T - ▁AS - ▁HER - ▁IS - ▁BE - ▁BUT - ▁NOT - ▁SHE - D - ▁AT - ▁ON - LY - ▁HIM - ▁THEY - ▁ALL - ▁HAVE - ▁BY - ▁SO - ▁THIS - ▁MY - ▁WHICH - ▁ME - ▁SAID - ▁FROM - ▁ONE - Y - E - ▁WERE - ▁WE - ▁NO - N - ▁THERE - ▁OR - ER - ▁AN - ▁WHEN - ▁ARE - ▁THEIR - ▁WOULD - ▁IF - ▁WHAT - ▁THEM - ▁WHO - ▁OUT - M - ▁DO - ▁WILL - ▁UP - ▁BEEN - P - R - ▁MAN - ▁THEN - ▁COULD - ▁MORE - C - ▁INTO - ▁NOW - ▁VERY - ▁YOUR - ▁SOME - ▁LITTLE - ES - ▁TIME - RE - ▁CAN - ▁LIKE - LL - ▁ABOUT - ▁HAS - ▁THAN - ▁DID - ▁UPON - ▁OVER - IN - ▁ANY - ▁WELL - ▁ONLY - B - ▁SEE - ▁GOOD - ▁OTHER - ▁TWO - L - ▁KNOW - ▁GO - ▁DOWN - ▁BEFORE - A - AL - ▁OUR - ▁OLD - ▁SHOULD - ▁MADE - ▁AFTER - ▁GREAT - ▁DAY - ▁MUST - ▁COME - ▁HOW - ▁SUCH - ▁CAME - LE - ▁WHERE - ▁US - ▁NEVER - ▁THESE - ▁MUCH - ▁DE - ▁MISTER - ▁WAY - G - ▁S - ▁MAY - ATION - ▁LONG - OR - ▁AM - ▁FIRST - ▁BACK - ▁OWN - ▁RE - ▁AGAIN - ▁SAY - ▁MEN - ▁WENT - ▁HIMSELF - ▁HERE - NESS - ▁THINK - V - IC - ▁EVEN - ▁THOUGHT - ▁HAND - ▁JUST - ▁O - ▁UN - VE - ION - ▁ITS - 'ON' - ▁MAKE - ▁MIGHT - ▁TOO - K - ▁AWAY - ▁LIFE - TH - ▁WITHOUT - ST - ▁THROUGH - ▁MOST - ▁TAKE - ▁DON - ▁EVERY - F - O - ▁SHALL - ▁THOSE - ▁EYES - AR - ▁STILL - ▁LAST - ▁HOUSE - ▁HEAD - ABLE - ▁NOTHING - ▁NIGHT - ITY - ▁LET - ▁MANY - ▁OFF - ▁BEING - ▁FOUND - ▁WHILE - EN - ▁SAW - ▁GET - ▁PEOPLE - ▁FACE - ▁YOUNG - CH - ▁UNDER - ▁ONCE - ▁TELL - AN - ▁THREE - ▁PLACE - ▁ROOM - ▁YET - ▁SAME - IL - US - U - ▁FATHER - ▁RIGHT - EL - ▁THOUGH - ▁ANOTHER - LI - RI - ▁HEART - IT - ▁PUT - ▁TOOK - ▁GIVE - ▁EVER - ▁E - ▁PART - ▁WORK - ERS - ▁LOOK - ▁NEW - ▁KING - ▁MISSUS - ▁SIR - ▁LOVE - ▁MIND - ▁LOOKED - W - RY - ▁ASKED - ▁LEFT - ET - ▁LIGHT - CK - ▁DOOR - ▁MOMENT - RO - ▁WORLD - ▁THINGS - ▁HOME - UL - ▁THING - LA - ▁WHY - ▁MOTHER - ▁ALWAYS - ▁FAR - FUL - ▁WATER - CE - IVE - UR - ▁HEARD - ▁SOMETHING - ▁SEEMED - I - LO - ▁BECAUSE - OL - ▁END - ▁TOLD - ▁CON - ▁YES - ▁GOING - ▁GOT - RA - IR - ▁WOMAN - ▁GOD - EST - TED - ▁FIND - ▁KNEW - ▁SOON - ▁EACH - ▁SIDE - H - TON - MENT - ▁OH - NE - Z - LING - ▁AGAINST - TER - ▁NAME - ▁MISS - ▁QUITE - ▁WANT - ▁YEARS - ▁FEW - ▁BETTER - ENT - ▁HALF - ▁DONE - ▁ALSO - ▁BEGAN - ▁HAVING - ▁ENOUGH - IS - ▁LADY - ▁WHOLE - LESS - ▁BOTH - ▁SEEN - ▁SET - ▁WHITE - ▁COURSE - IES - ▁VOICE - ▁CALLED - ▁D - ▁EX - ATE - ▁TURNED - ▁GAVE - ▁C - ▁POOR - MAN - UT - NA - ▁DEAR - ISH - ▁GIRL - ▁MORNING - ▁BETWEEN - LED - ▁NOR - IA - ▁AMONG - MA - ▁ - ▁SMALL - ▁REST - ▁WHOM - ▁FELT - ▁HANDS - ▁MYSELF - ▁HIGH - ▁M - ▁HOWEVER - ▁HERSELF - ▁P - CO - ▁STOOD - ID - ▁KIND - ▁HUNDRED - AS - ▁ROUND - ▁ALMOST - TY - ▁SINCE - ▁G - AM - ▁LA - SE - ▁BOY - ▁MA - ▁PERHAPS - ▁WORDS - ATED - ▁HO - X - ▁MO - ▁SAT - ▁REPLIED - ▁FOU