| --- |
| tags: |
| - espnet |
| - audio |
| - automatic-speech-recognition |
| language: bh |
| datasets: |
| - respin_small |
| license: cc-by-4.0 |
| --- |
| |
| ## ESPnet2 ASR model |
|
|
| ### `SpireLab/spire_respin_baselines_espnet` |
| |
| This model was trained by wtc7 using respin_small 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 |
| |
| pip install -e . |
| cd egs2/respin_small/asr1 |
| ./run.sh --skip_data_prep false --skip_train true --download_model SpireLab/spire_respin_baselines_espnet |
| ``` |
|
|
| <!-- Generated by scripts/utils/show_asr_result.sh --> |
| # RESULTS |
| ## Environments |
| - date: `Sun May 25 02:31:02 IST 2025` |
| - python version: `3.8.10 (default, Mar 18 2025, 20:04:55) [GCC 9.4.0]` |
| - espnet version: `espnet 202412` |
| - pytorch version: `pytorch 2.3.0+cu121` |
| - Git hash: `0fe7b8581fbc68841eb48776f052aa9a5989108c` |
| - Commit date: `Tue Jan 14 20:06:15 2025 -0500` |
|
|
| ## exp_small/exp_bh/asr_bh_ebf_size256_mlp1024_lin1024_e8_mactrue_bs6M_gacc1 |
| ### WER |
| |
| |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
| |---|---|---|---|---|---|---|---|---| |
| |decode_lid_asr_model_valid.acc.ave/test_bh|2220|22453|85.9|13.4|0.7|1.1|15.2|73.2| |
|
|
| ### CER |
|
|
| |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
| |---|---|---|---|---|---|---|---|---| |
| |decode_lid_asr_model_valid.acc.ave/test_bh|2220|104745|96.8|2.1|1.1|1.2|4.4|73.2| |
| |
| ### TER |
| |
| |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |
| |---|---|---|---|---|---|---|---|---| |
| |
| ## ASR config |
| |
| <details><summary>expand</summary> |
| |
| ``` |
| config: conf/tuning/train_asr_e_branchformer_size256_mlp1024_linear1024_e8_mactrue_bs6M_gacc1.yaml |
| print_config: false |
| log_level: INFO |
| drop_last_iter: false |
| dry_run: false |
| iterator_type: sequence |
| valid_iterator_type: null |
| output_dir: exp_small/exp_bh/asr_bh_ebf_size256_mlp1024_lin1024_e8_mactrue_bs6M_gacc1 |
| ngpu: 1 |
| seed: 2022 |
| num_workers: 8 |
| 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 |
| use_deepspeed: false |
| deepspeed_config: null |
| cudnn_enabled: true |
| cudnn_benchmark: false |
| cudnn_deterministic: true |
| use_tf32: false |
| collect_stats: false |
| write_collected_feats: false |
| max_epoch: 70 |
| patience: 5 |
| val_scheduler_criterion: |
| - valid |
| - loss |
| early_stopping_criterion: |
| - valid |
| - loss |
| - min |
| best_model_criterion: |
| - - valid |
| - acc |
| - max |
| keep_nbest_models: 5 |
| 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: true |
| 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: [] |
| num_iters_per_epoch: null |
| batch_size: 20 |
| valid_batch_size: null |
| batch_bins: 6000000 |
| valid_batch_bins: null |
| category_sample_size: 10 |
| train_shape_file: |
| - exp_small/exp_bh/asr_stats_raw_bh_char_sp/train/speech_shape |
| - exp_small/exp_bh/asr_stats_raw_bh_char_sp/train/text_shape.char |
| valid_shape_file: |
| - exp_small/exp_bh/asr_stats_raw_bh_char_sp/valid/speech_shape |
| - exp_small/exp_bh/asr_stats_raw_bh_char_sp/valid/text_shape.char |
| batch_type: numel |
| 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/bh/raw/train_bh_sp/wav.scp |
| - speech |
| - sound |
| - - dump/bh/raw/train_bh_sp/text |
| - text |
| - text |
| valid_data_path_and_name_and_type: |
| - - dump/bh/raw/dev_bh/wav.scp |
| - speech |
| - sound |
| - - dump/bh/raw/dev_bh/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: 0.002 |
| weight_decay: 1.0e-06 |
| scheduler: warmuplr |
| scheduler_conf: |
| warmup_steps: 15000 |
| token_list: |
| - <blank> |
| - <unk> |
| - <space> |
| - ा |
| - े |
| - क |
| - र |
| - ल |
| - स |
| - न |
| - म |
| - त |
| - ी |
| - ि |
| - ह |
| - ब |
| - ् |
| - प |
| - व |
| - ज |
| - ं |
| - ो |
| - द |
| - ख |
| - य |
| - ग |
| - ट |
| - ु |
| - अ |
| - ई |
| - इ |
| - च |
| - भ |
| - आ |
| - ू |
| - उ |
| - ए |
| - श |
| - ै |
| - ध |
| - ड |
| - फ |
| - ड़ |
| - ौ |
| - . |
| - छ |
| - ण |
| - ष |
| - थ |
| - ओ |
| - ढ़ |
| - घ |
| - ठ |
| - ॉ |
| - ृ |
| - ढ |
| - ऑ |
| - ँ |
| - ऊ |
| - ऋ |
| - औ |
| - झ |
| - ज़ |
| - फ़ |
| - ऐ |
| - ञ |
| - ऽ |
| - ख़ |
| - क़ |
| - ़ |
| - ः |
| - ॅ |
| - ऱ |
| - <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: char |
| 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' |
| short_noise_thres: 0.5 |
| aux_ctc_tasks: [] |
| frontend: default |
| frontend_conf: |
| n_fft: 512 |
| win_length: 400 |
| hop_length: 160 |
| 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 |
| preencoder: null |
| preencoder_conf: {} |
| encoder: e_branchformer |
| encoder_conf: |
| output_size: 256 |
| attention_heads: 4 |
| attention_layer_type: rel_selfattn |
| pos_enc_layer_type: rel_pos |
| rel_pos_type: latest |
| cgmlp_linear_units: 1024 |
| cgmlp_conv_kernel: 31 |
| use_linear_after_conv: false |
| gate_activation: identity |
| num_blocks: 8 |
| dropout_rate: 0.1 |
| positional_dropout_rate: 0.1 |
| attention_dropout_rate: 0.1 |
| input_layer: conv2d2 |
| layer_drop_rate: 0.0 |
| linear_units: 1024 |
| positionwise_layer_type: linear |
| use_ffn: true |
| macaron_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: 0.0 |
| preprocessor: default |
| preprocessor_conf: {} |
| required: |
| - output_dir |
| - token_list |
| version: '202409' |
| distributed: false |
| ``` |
| |
| </details> |
|
|
|
|
|
|
| ### 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} |
| } |
| ``` |
|
|
