--- tags: - espnet - audio - automatic-speech-recognition language: gvc datasets: - americasnlp22 license: cc-by-4.0 --- ## ESPnet2 ASR model ### `espnet/americasnlp22-asr-gvc` This model was trained by Pavel Denisov using americasnlp22 recipe in [espnet](https://github.com/espnet/espnet/). ### Demo: How to use in ESPnet2 ```bash cd espnet git checkout 66ca5df9f08b6084dbde4d9f312fa8ba0a47ecfc pip install -e . cd egs2/americasnlp22/asr1 ./run.sh \ --skip_data_prep false \ --skip_train true \ --download_model espnet/americasnlp22-asr-gvc \ --lang gvc \ --local_data_opts "--lang gvc" \ --train_set train_gvc \ --valid_set dev_gvc \ --test_sets dev_gvc \ --gpu_inference false \ --inference_nj 8 \ --lm_train_text data/train_gvc/text \ --bpe_train_text data/train_gvc/text ``` # RESULTS ## Environments - date: `Sun Jun 5 03:29:33 CEST 2022` - python version: `3.9.13 (main, May 18 2022, 00:00:00) [GCC 11.3.1 20220421 (Red Hat 11.3.1-2)]` - espnet version: `espnet 202204` - pytorch version: `pytorch 1.11.0+cu115` - Git hash: `d55704daa36d3dd2ca24ae3162ac40d81957208c` - Commit date: `Wed Jun 1 02:33:09 2022 +0200` ## asr_train_asr_transformer_raw_gvc_bpe100_sp ### WER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |decode_asr_asr_model_valid.cer_ctc.best/dev_gvc|253|2206|12.4|72.4|15.1|6.7|94.2|99.6| ### CER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |decode_asr_asr_model_valid.cer_ctc.best/dev_gvc|253|13453|64.7|15.5|19.9|10.2|45.6|99.6| ### TER |dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err| |---|---|---|---|---|---|---|---|---| |decode_asr_asr_model_valid.cer_ctc.best/dev_gvc|253|10229|58.3|22.3|19.4|11.0|52.7|99.6| ## ASR config
expand ``` config: conf/train_asr_transformer.yaml print_config: false log_level: INFO dry_run: false iterator_type: sequence output_dir: exp/asr_train_asr_transformer_raw_gvc_bpe100_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: 15 patience: null val_scheduler_criterion: - valid - loss early_stopping_criterion: - valid - loss - min best_model_criterion: - - valid - cer_ctc - min keep_nbest_models: 1 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.model.feature_extractor - frontend.upstream.model.encoder.layers.0 - frontend.upstream.model.encoder.layers.1 - frontend.upstream.model.encoder.layers.2 - frontend.upstream.model.encoder.layers.3 - frontend.upstream.model.encoder.layers.4 - frontend.upstream.model.encoder.layers.5 - frontend.upstream.model.encoder.layers.6 - frontend.upstream.model.encoder.layers.7 - frontend.upstream.model.encoder.layers.8 - frontend.upstream.model.encoder.layers.9 - frontend.upstream.model.encoder.layers.10 - frontend.upstream.model.encoder.layers.11 - frontend.upstream.model.encoder.layers.12 - frontend.upstream.model.encoder.layers.13 - frontend.upstream.model.encoder.layers.14 - frontend.upstream.model.encoder.layers.15 - frontend.upstream.model.encoder.layers.16 - frontend.upstream.model.encoder.layers.17 - frontend.upstream.model.encoder.layers.18 - frontend.upstream.model.encoder.layers.19 - frontend.upstream.model.encoder.layers.20 - frontend.upstream.model.encoder.layers.21 num_iters_per_epoch: null batch_size: 20 valid_batch_size: null batch_bins: 200000 valid_batch_bins: null train_shape_file: - exp/asr_stats_raw_gvc_bpe100_sp/train/speech_shape - exp/asr_stats_raw_gvc_bpe100_sp/train/text_shape.bpe valid_shape_file: - exp/asr_stats_raw_gvc_bpe100_sp/valid/speech_shape - exp/asr_stats_raw_gvc_bpe100_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_gvc_sp/wav.scp - speech - sound - - dump/raw/train_gvc_sp/text - text - text valid_data_path_and_name_and_type: - - dump/raw/dev_gvc/wav.scp - speech - sound - - dump/raw/dev_gvc/text - text - text allow_variable_data_keys: false max_cache_size: 0.0 max_cache_fd: 32 valid_max_cache_size: null optim: adamw optim_conf: lr: 0.0001 scheduler: warmuplr scheduler_conf: warmup_steps: 300 token_list: - - - ▁ - a - '''' - u - i - o - h - U - . - ro - re - ri - ka - s - na - p - e - ▁ti - t - ':' - d - ha - 'no' - ▁hi - m - ▁ni - '~' - ã - ta - ▁wa - ti - ',' - ▁to - b - n - ▁kh - ma - r - se - w - l - k - '"' - ñ - õ - g - ( - ) - v - f - '?' - A - K - z - é - T - '!' - D - ó - N - á - R - P - ú - '0' - í - I - '1' - L - '-' - '8' - E - S - Ã - F - '9' - '6' - G - C - x - '3' - '2' - B - W - J - H - Y - M - j - ç - q - c - Ñ - '4' - '7' - O - y - init: null input_size: null ctc_conf: dropout_rate: 0.0 ctc_type: builtin reduce: true ignore_nan_grad: true joint_net_conf: null use_preprocessor: true token_type: bpe bpemodel: data/gvc_token_list/bpe_unigram100/bpe.model 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: wav2vec2_url upstream_ckpt: https://dl.fbaipublicfiles.com/fairseq/wav2vec/xlsr2_300m.pt download_dir: ./hub multilayer_feature: true fs: 16k specaug: null specaug_conf: {} normalize: utterance_mvn normalize_conf: {} model: espnet model_conf: ctc_weight: 1.0 lsm_weight: 0.0 length_normalized_loss: false extract_feats_in_collect_stats: false preencoder: linear preencoder_conf: input_size: 1024 output_size: 80 encoder: transformer encoder_conf: input_layer: conv2d2 num_blocks: 1 linear_units: 2048 dropout_rate: 0.2 output_size: 256 attention_heads: 8 attention_dropout_rate: 0.2 postencoder: null postencoder_conf: {} decoder: rnn decoder_conf: {} required: - output_dir - token_list version: '202204' 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} } ```