--- tags: - espnet - audio - automatic-speech-recognition language: en datasets: - swbd_da license: cc-by-4.0 --- ## ESPnet2 ASR model ### `akreal/espnet2_swbd_da_hubert_conformer` This model was trained by Pavel Denisov using swbd_da recipe in [espnet](https://github.com/espnet/espnet/). ### Demo: How to use in ESPnet2 ```bash cd espnet git checkout 08c6efbc6299c972301236625f9abafe087c9f9c pip install -e . cd egs2/swbd_da/asr1 ./run.sh --skip_data_prep false --skip_train true --download_model espnet/akreal_swbd_da_hubert_conformer ``` # RESULTS ## Environments - date: `Thu Jan 20 19:31:21 CET 2022` - python version: `3.8.12 (default, Aug 30 2021, 00:00:00) [GCC 11.2.1 20210728 (Red Hat 11.2.1-1)]` - espnet version: `espnet 0.10.6a1` - pytorch version: `pytorch 1.10.1+cu113` - Git hash: `08c6efbc6299c972301236625f9abafe087c9f9c` - Commit date: `Tue Jan 4 13:40:33 2022 +0100` ## asr_train_asr_raw_en_word_sp ### WER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |decode_asr_asr_model_valid.loss.ave/test_context3|2379|2379|66.3|33.7|0.0|0.0|33.7|33.7| |decode_asr_asr_model_valid.loss.ave/valid_context3|8116|8116|69.5|30.5|0.0|0.0|30.5|30.5| ### CER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |decode_asr_asr_model_valid.loss.ave/test_context3|2379|19440|76.1|17.7|6.2|8.1|32.0|33.7| |decode_asr_asr_model_valid.loss.ave/valid_context3|8116|66353|79.5|16.1|4.4|8.0|28.5|30.5| ### TER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| ## ASR config
expand ``` config: conf/tuning/train_asr_conformer_hubert_context3.yaml print_config: false log_level: INFO dry_run: false iterator_type: sequence output_dir: exp/asr_train_asr_conformer_hubert_context3_raw_en_word_sp 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: 35 patience: null val_scheduler_criterion: - valid - loss early_stopping_criterion: - valid - loss - min best_model_criterion: - - valid - loss - min keep_nbest_models: 7 nbest_averaging_interval: 0 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_matplotlib: true use_tensorboard: true use_wandb: false wandb_project: null wandb_id: null wandb_entity: null wandb_name: null wandb_model_log_interval: -1 detect_anomaly: false pretrain_path: null init_param: [] ignore_init_mismatch: false freeze_param: - frontend.upstream num_iters_per_epoch: null batch_size: 20 valid_batch_size: null batch_bins: 4000000 valid_batch_bins: null train_shape_file: - exp/asr_stats_context3_raw_en_word_sp/train/speech_shape - exp/asr_stats_context3_raw_en_word_sp/train/text_shape.word valid_shape_file: - exp/asr_stats_context3_raw_en_word_sp/valid/speech_shape - exp/asr_stats_context3_raw_en_word_sp/valid/text_shape.word 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_context3_sp/wav.scp - speech - sound - - dump/raw/train_context3_sp/text - text - text valid_data_path_and_name_and_type: - - dump/raw/valid_context3/wav.scp - speech - sound - - dump/raw/valid_context3/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: 0.0001 scheduler: warmuplr scheduler_conf: warmup_steps: 25000 token_list: - - - statement - backchannel - opinion - abandon - agree - yn_q - apprec - 'yes' - uninterp - close - wh_q - acknowledge - 'no' - yn_decl_q - hedge - backchannel_q - sum - quote - affirm - other - directive - repeat - open_q - completion - rhet_q - hold - reject - answer - neg - ans_dispref - repeat_q - open - or - commit - maybe - decl_q - third_pty - self_talk - thank - apology - tag_q - downplay - init: null input_size: null ctc_conf: dropout_rate: 0.0 ctc_type: builtin reduce: true ignore_nan_grad: true joint_net_conf: null model_conf: ctc_weight: 0.0 extract_feats_in_collect_stats: false use_preprocessor: true token_type: word bpemodel: null 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' 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 - 30 num_freq_mask: 2 apply_time_mask: true time_mask_width_range: - 0 - 40 num_time_mask: 2 normalize: utterance_mvn normalize_conf: {} preencoder: linear preencoder_conf: input_size: 1024 output_size: 80 encoder: conformer encoder_conf: output_size: 512 attention_heads: 8 linear_units: 2048 num_blocks: 12 dropout_rate: 0.1 positional_dropout_rate: 0.1 attention_dropout_rate: 0.1 input_layer: conv2d normalize_before: true macaron_style: true pos_enc_layer_type: rel_pos selfattention_layer_type: rel_selfattn activation_type: swish use_cnn_module: true cnn_module_kernel: 31 postencoder: null postencoder_conf: {} decoder: transformer decoder_conf: attention_heads: 8 linear_units: 2048 num_blocks: 6 dropout_rate: 0.1 positional_dropout_rate: 0.1 self_attention_dropout_rate: 0.1 src_attention_dropout_rate: 0.1 required: - output_dir - token_list version: 0.10.5a1 distributed: false ```
### Citing ESPnet ```BibTex @inproceedings{watanabe2018espnet, author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai}, title={{ESPnet}: End-to-End Speech Processing Toolkit}, year={2018}, booktitle={Proceedings of Interspeech}, pages={2207--2211}, doi={10.21437/Interspeech.2018-1456}, url={http://dx.doi.org/10.21437/Interspeech.2018-1456} } ``` or arXiv: ```bibtex @misc{watanabe2018espnet, title={ESPnet: End-to-End Speech Processing Toolkit}, author={Shinji Watanabe and Takaaki Hori and Shigeki Karita and Tomoki Hayashi and Jiro Nishitoba and Yuya Unno and Nelson Yalta and Jahn Heymann and Matthew Wiesner and Nanxin Chen and Adithya Renduchintala and Tsubasa Ochiai}, year={2018}, eprint={1804.00015}, archivePrefix={arXiv}, primaryClass={cs.CL} } ```