--- tags: - espnet - audio - automatic-speech-recognition language: en datasets: - A license: cc-by-4.0 --- ## ESPnet2 ASR model ### `espnet/jiyang_tang_aphsiabank_english_asr_ebranchformer_small_wavlm_large1` This model was trained by Jiyang Tang using A recipe in [espnet](https://github.com/espnet/espnet/). ### Demo: How to use in ESPnet2 Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html) if you haven't done that already. ```bash cd espnet git checkout 4ddda8634b6b03fbbdae97927e58722a13f1f7c8 pip install -e . cd jtang1/A/asr1 ./run.sh --skip_data_prep false --skip_train true --download_model espnet/jiyang_tang_aphsiabank_english_asr_ebranchformer_small_wavlm_large1 ``` # RESULTS ## Environments - date: `Mon Mar 13 15:37:27 EDT 2023` - python version: `3.9.12 (main, Apr 5 2022, 06:56:58) [GCC 7.5.0]` - espnet version: `espnet 202301` - pytorch version: `pytorch 1.8.1` - Git hash: `b0b2a0aa9c335267046e83036b87e88af30698da` - Commit date: `Tue Feb 7 14:56:31 2023 -0500` ## asr_ebranchformer_wavlm ### WER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |decode_asr_model_valid.acc.ave/test|28424|240039|81.3|13.2|5.6|3.4|22.2|67.6| ### CER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |decode_asr_model_valid.acc.ave/test|28424|1103375|89.9|4.1|6.0|3.7|13.8|67.6| ### TER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| ## ASR config
expand ``` config: conf/tuning/train_asr_ebranchformer_small_wavlm_large1.yaml print_config: false log_level: INFO dry_run: false iterator_type: sequence output_dir: exp/asr_ebranchformer_wavlm ngpu: 1 seed: 2022 num_workers: 2 num_att_plot: 0 dist_backend: nccl dist_init_method: env:// dist_world_size: 2 dist_rank: 0 local_rank: 0 dist_master_addr: localhost dist_master_port: 47613 dist_launcher: null multiprocessing_distributed: true unused_parameters: true sharded_ddp: false cudnn_enabled: true cudnn_benchmark: false cudnn_deterministic: false collect_stats: false write_collected_feats: false max_epoch: 30 patience: null val_scheduler_criterion: - valid - loss early_stopping_criterion: - valid - loss - min best_model_criterion: - - valid - acc - max keep_nbest_models: 10 nbest_averaging_interval: 0 grad_clip: 5 grad_clip_type: 2.0 grad_noise: false accum_grad: 8 no_forward_run: false resume: true train_dtype: float32 use_amp: true log_interval: 200 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 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: 6000000 valid_batch_bins: null train_shape_file: - exp/asr_stats_raw_en_char_sp/train/speech_shape - exp/asr_stats_raw_en_char_sp/train/text_shape.char valid_shape_file: - exp/asr_stats_raw_en_char_sp/valid/speech_shape - exp/asr_stats_raw_en_char_sp/valid/text_shape.char 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_sp/wav.scp - speech - sound - - dump/raw/train_sp/text - text - text valid_data_path_and_name_and_type: - - dump/raw/val/wav.scp - speech - sound - - dump/raw/val/text - text - text allow_variable_data_keys: false max_cache_size: 0.0 max_cache_fd: 32 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: warmuplr scheduler_conf: warmup_steps: 2500 token_list: - - - '[APH]' - '[NONAPH]' - - e - t - a - h - o - n - i - s - d - r - u - l - m - w - y - g - c - b - f - p - k - '''' - v - j - < - L - A - U - '>' - ɪ - x - ə - z - ɛ - ɑ - q - ɹ - æ - ˞ - ʌ - ʃ - ʊ - ɔ - ŋ - ɚ - ɾ - ʒ - ð - θ - ɜ - ɝ - ɡ - '0' - ː - ʔ - ɒ - é - ɸ - ̩ - ʤ - ʧ - init: null input_size: null ctc_conf: dropout_rate: 0.0 ctc_type: builtin reduce: true ignore_nan_grad: null zero_infinity: true joint_net_conf: null use_preprocessor: true token_type: char bpemodel: null non_linguistic_symbols: local/nlsyms.txt 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: wavlm_large 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: 5 normalize: utterance_mvn normalize_conf: {} model: espnet model_conf: ctc_weight: 0.3 lsm_weight: 0.1 length_normalized_loss: false extract_feats_in_collect_stats: false preencoder: linear preencoder_conf: input_size: 1024 output_size: 80 encoder: e_branchformer encoder_conf: output_size: 256 attention_heads: 4 linear_units: 1024 num_blocks: 12 dropout_rate: 0.1 positional_dropout_rate: 0.1 attention_dropout_rate: 0.1 layer_drop_rate: 0.1 input_layer: conv2d1 macaron_ffn: true pos_enc_layer_type: rel_pos attention_layer_type: rel_selfattn rel_pos_type: latest cgmlp_linear_units: 3072 cgmlp_conv_kernel: 31 use_linear_after_conv: false gate_activation: identity positionwise_layer_type: linear use_ffn: true merge_conv_kernel: 31 postencoder: null postencoder_conf: {} 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: 0.1 src_attention_dropout_rate: 0.1 layer_drop_rate: 0.2 preprocessor: default preprocessor_conf: {} required: - output_dir - token_list version: '202301' distributed: true ```
### 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} } ```