--- tags: - espnet - audio - automatic-speech-recognition language: en datasets: - slue-voxceleb license: cc-by-4.0 --- ## ESPnet2 ASR model ### `espnet/sluevoxceleb_wavlm_lightweight_sa` This model was trained by “siddhu001” using slue-voxceleb 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 e23ef85f0b3116ad5c60d0833f186da0deec0734 pip install -e . cd egs2/slue-voxceleb/slu1_superb_correct ./run.sh --skip_data_prep false --skip_train true --download_model espnet/sluevoxceleb_wavlm_lightweight_sa ``` # RESULTS ## Environments - date: `Wed Feb 7 23:05:29 CST 2024` - python version: `3.9.13 (main, Aug 25 2022, 23:26:10) [GCC 11.2.0]` - espnet version: `espnet 202310` - pytorch version: `pytorch 2.1.0+cu121` - Git hash: `21d2105784e4da98397bf487b2550d4c6e16d40d` - Commit date: `Wed Jan 31 13:40:37 2024 -0600` ## exp/slu_train_asr_wavlm_large_0.01_raw_en_word_sp ### WER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |decode_asr_slu_model_valid.loss.ave/devel|1436|1436|73.2|26.8|0.0|0.0|26.8|26.8| |decode_asr_slu_model_valid.loss.ave/test|3426|3426|73.0|27.0|0.0|0.0|27.0|27.0| ### CER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |decode_asr_slu_model_valid.loss.ave/devel|1436|10365|77.0|20.7|2.3|1.3|24.4|26.8| |decode_asr_slu_model_valid.loss.ave/test|3426|24887|77.1|20.5|2.4|1.2|24.1|27.0| ### TER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| ## exp/slu_train_asr_wavlm_large_0.01_raw_en_word_sp/decode_asr_slu_model_valid.loss.ave ### WER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |org/devel|1437|1437|73.2|26.8|0.0|0.0|26.8|26.8| ### CER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |org/devel|1437|10372|77.0|20.7|2.3|1.3|24.3|26.8| ### TER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| ## ASR config
expand ``` config: conf/train_asr_wavlm_large_0.01.yaml print_config: false log_level: INFO drop_last_iter: false dry_run: false iterator_type: sequence valid_iterator_type: null output_dir: exp/slu_train_asr_wavlm_large_0.01_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: 4 dist_rank: 0 local_rank: 0 dist_master_addr: localhost dist_master_port: 53613 dist_launcher: null multiprocessing_distributed: true unused_parameters: true sharded_ddp: false cudnn_enabled: true cudnn_benchmark: false cudnn_deterministic: true collect_stats: false write_collected_feats: false max_epoch: 50 patience: null val_scheduler_criterion: - valid - loss early_stopping_criterion: - valid - loss - min best_model_criterion: - - valid - loss - min keep_nbest_models: 10 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 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_lora: false save_lora_only: true lora_conf: {} pretrain_path: null init_param: [] ignore_init_mismatch: false freeze_param: - frontend.upstream num_iters_per_epoch: null batch_size: 320 valid_batch_size: null batch_bins: 1000000 valid_batch_bins: null train_shape_file: - exp/slu_stats_raw_en_word_sp/train/speech_shape - exp/slu_stats_raw_en_word_sp/train/text_shape.word valid_shape_file: - exp/slu_stats_raw_en_word_sp/valid/speech_shape - exp/slu_stats_raw_en_word_sp/valid/text_shape.word batch_type: folded 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 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/devel/wav.scp - speech - sound - - dump/raw/devel/text - text - text 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: 0.01 scheduler: warmuplr scheduler_conf: warmup_steps: 1000 token_list: - - - Neutral - Positive - Negative - transcript_token_list: null two_pass: false pre_postencoder_norm: false 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 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' short_noise_thres: 0.5 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 - 30 num_freq_mask: 2 apply_time_mask: true time_mask_width_range: - 0 - 40 num_time_mask: 2 normalize: utterance_mvn normalize_conf: {} model: espnet model_conf: ctc_weight: 0.0 lsm_weight: 0.0 length_normalized_loss: false superb_setup: true num_class: 3 ssl_input_size: 1024 extract_feats_in_collect_stats: false preencoder: null preencoder_conf: {} encoder: rnn encoder_conf: {} postencoder: null postencoder_conf: {} deliberationencoder: null deliberationencoder_conf: {} decoder: rnn decoder_conf: {} postdecoder: null postdecoder_conf: {} required: - output_dir - token_list version: '202310' 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} } ```