Update model

README.md

@@ -1,3 +1,390 @@
----
-license: cc-by-4.0
----
+---
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+language: en
+datasets:
+- myst_ogi_cmu_kids
+license: cc-by-4.0
+---
+
+## ESPnet2 ASR model
+
+### `espnet/myst_ogi_cmu_kids_aed_upsample`
+
+This model was trained by eric102004 using myst_ogi_cmu_kids 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 6f722aee1f9593572d5eddfd8cac7075b07cf9ca
+pip install -e .
+cd egs2/myst_ogi_cmu_kids/asr1
+./run.sh --skip_data_prep false --skip_train true --download_model espnet/myst_ogi_cmu_kids_aed_upsample
+```
+
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Wed Feb 19 19:12:32 CST 2025`
+- python version: `3.12.3 | packaged by Anaconda, Inc. | (main, May  6 2024, 19:46:43) [GCC 11.2.0]`
+- espnet version: `espnet 202412`
+- pytorch version: `pytorch 2.4.0`
+- Git hash: `6f722aee1f9593572d5eddfd8cac7075b07cf9ca`
+  - Commit date: `Thu Feb 6 22:32:07 2025 -0600`
+
+## exp/asr_train_asr_lr002_raw_en_char_dur05_filter_ba_h2l4/decode_asr_asr_model_valid.cer.ave_10best
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|data_cmu/dev|237|2170|89.1|8.7|2.2|2.4|13.3|37.1|
+|data_cmu/test|475|4287|88.3|9.0|2.6|2.4|14.0|40.0|
+|data_jibo/dev|853|853|19.1|80.9|0.0|219.0|299.9|97.4|
+|data_jibo/test|1044|1044|20.4|79.6|0.0|306.0|385.6|94.1|
+|data_myst/dev|9037|153273|90.4|7.7|1.8|2.9|12.5|66.8|
+|data_myst/test|10311|182712|89.9|7.8|2.3|3.1|13.1|65.0|
+|data_ogi_scripted/dev|5426|15375|98.7|1.1|0.2|0.2|1.5|2.2|
+|data_ogi_scripted/test|15945|45419|98.5|1.2|0.3|0.3|1.9|2.7|
+|data_ogi_spon/dev|349|13561|81.0|15.2|3.8|3.2|22.2|96.6|
+|data_ogi_spon/test|1095|38811|81.8|14.9|3.3|3.8|22.0|95.3|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|data_cmu/dev|237|11449|94.9|2.5|2.6|2.4|7.4|37.1|
+|data_cmu/test|475|22664|94.4|2.3|3.3|2.2|7.8|40.0|
+|data_jibo/dev|853|2558|55.8|33.3|10.9|362.2|406.4|97.4|
+|data_jibo/test|1044|3259|62.1|29.5|8.4|498.7|536.6|94.1|
+|data_myst/dev|9037|763728|96.2|1.8|2.0|2.9|6.7|66.8|
+|data_myst/test|10311|911898|95.8|1.8|2.4|3.1|7.3|65.0|
+|data_ogi_scripted/dev|5426|83141|99.0|0.5|0.4|0.3|1.2|2.2|
+|data_ogi_scripted/test|15945|244467|98.8|0.6|0.5|0.4|1.5|2.7|
+|data_ogi_spon/dev|349|58255|90.3|4.8|4.9|3.7|13.4|96.6|
+|data_ogi_spon/test|1095|165977|90.9|4.6|4.5|4.3|13.4|95.3|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+
+## ASR config
+
+<details><summary>expand</summary>
+
+```
+config: conf/tuning/train_asr_lr002.yaml
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: sequence
+valid_iterator_type: null
+output_dir: exp/asr_train_asr_lr002_raw_en_char_dur05_filter_ba_h2l4
+ngpu: 1
+seed: 2022
+num_workers: 4
+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
+static_graph: false
+gradient_as_bucket_view: false
+broadcast_buffers: true
+bucket_cap_mb: 25
+compress_gradients: false
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+use_tf32: false
+collect_stats: false
+write_collected_feats: false
+max_epoch: 70
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - cer
+    - min
+keep_nbest_models: 10
+nbest_averaging_interval: 0
+grad_clip: 5.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 4
+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: 16000000
+valid_batch_bins: null
+category_sample_size: 10
+train_shape_file:
+- exp/asr_stats_raw_en_char_ba_h2l4/train/speech_shape
+- exp/asr_stats_raw_en_char_ba_h2l4/train/text_shape.char
+valid_shape_file:
+- exp/asr_stats_raw_en_char_ba_h2l4/valid/speech_shape
+- exp/asr_stats_raw_en_char_ba_h2l4/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
+validate_each_iter_factory: true
+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_no_special_ba_h2l4/raw/train/wav.scp
+    - speech
+    - sound
+-   - dump_no_special_ba_h2l4/raw/train/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump_no_special_ba_h2l4/raw/dev/wav.scp
+    - speech
+    - sound
+-   - dump_no_special_ba_h2l4/raw/dev/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>
+- E
+- T
+- A
+- O
+- I
+- N
+- H
+- S
+- R
+- L
+- D
+- U
+- W
+- M
+- C
+- G
+- Y
+- B
+- P
+- F
+- K
+- ''''
+- V
+- X
+- J
+- Z
+- Q
+- ','
+- '-'
+- <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: 12
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d
+    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: {}
+masker: null
+masker_conf: {}
+required:
+- output_dir
+- token_list
+version: '202412'
+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}
+}
+```

exp/asr_train_asr_lr002_raw_en_char_dur05_filter_ba_h2l4/RESULTS.md

@@ -0,0 +1,45 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Wed Feb 19 19:12:32 CST 2025`
+- python version: `3.12.3 | packaged by Anaconda, Inc. | (main, May  6 2024, 19:46:43) [GCC 11.2.0]`
+- espnet version: `espnet 202412`
+- pytorch version: `pytorch 2.4.0`
+- Git hash: `6f722aee1f9593572d5eddfd8cac7075b07cf9ca`
+  - Commit date: `Thu Feb 6 22:32:07 2025 -0600`
+
+## exp/asr_train_asr_lr002_raw_en_char_dur05_filter_ba_h2l4/decode_asr_asr_model_valid.cer.ave_10best
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|data_cmu/dev|237|2170|89.1|8.7|2.2|2.4|13.3|37.1|
+|data_cmu/test|475|4287|88.3|9.0|2.6|2.4|14.0|40.0|
+|data_jibo/dev|853|853|19.1|80.9|0.0|219.0|299.9|97.4|
+|data_jibo/test|1044|1044|20.4|79.6|0.0|306.0|385.6|94.1|
+|data_myst/dev|9037|153273|90.4|7.7|1.8|2.9|12.5|66.8|
+|data_myst/test|10311|182712|89.9|7.8|2.3|3.1|13.1|65.0|
+|data_ogi_scripted/dev|5426|15375|98.7|1.1|0.2|0.2|1.5|2.2|
+|data_ogi_scripted/test|15945|45419|98.5|1.2|0.3|0.3|1.9|2.7|
+|data_ogi_spon/dev|349|13561|81.0|15.2|3.8|3.2|22.2|96.6|
+|data_ogi_spon/test|1095|38811|81.8|14.9|3.3|3.8|22.0|95.3|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|data_cmu/dev|237|11449|94.9|2.5|2.6|2.4|7.4|37.1|
+|data_cmu/test|475|22664|94.4|2.3|3.3|2.2|7.8|40.0|
+|data_jibo/dev|853|2558|55.8|33.3|10.9|362.2|406.4|97.4|
+|data_jibo/test|1044|3259|62.1|29.5|8.4|498.7|536.6|94.1|
+|data_myst/dev|9037|763728|96.2|1.8|2.0|2.9|6.7|66.8|
+|data_myst/test|10311|911898|95.8|1.8|2.4|3.1|7.3|65.0|
+|data_ogi_scripted/dev|5426|83141|99.0|0.5|0.4|0.3|1.2|2.2|
+|data_ogi_scripted/test|15945|244467|98.8|0.6|0.5|0.4|1.5|2.7|
+|data_ogi_spon/dev|349|58255|90.3|4.8|4.9|3.7|13.4|96.6|
+|data_ogi_spon/test|1095|165977|90.9|4.6|4.5|4.3|13.4|95.3|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|

exp/asr_train_asr_lr002_raw_en_char_dur05_filter_ba_h2l4/config.yaml

@@ -0,0 +1,271 @@
+config: conf/tuning/train_asr_lr002.yaml
+print_config: false
+log_level: INFO
+drop_last_iter: false
+dry_run: false
+iterator_type: sequence
+valid_iterator_type: null
+output_dir: exp/asr_train_asr_lr002_raw_en_char_dur05_filter_ba_h2l4
+ngpu: 1
+seed: 2022
+num_workers: 4
+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
+static_graph: false
+gradient_as_bucket_view: false
+broadcast_buffers: true
+bucket_cap_mb: 25
+compress_gradients: false
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+use_tf32: false
+collect_stats: false
+write_collected_feats: false
+max_epoch: 70
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - valid
+    - cer
+    - min
+keep_nbest_models: 10
+nbest_averaging_interval: 0
+grad_clip: 5.0
+grad_clip_type: 2.0
+grad_noise: false
+accum_grad: 4
+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: 16000000
+valid_batch_bins: null
+category_sample_size: 10
+train_shape_file:
+- exp/asr_stats_raw_en_char_ba_h2l4/train/speech_shape
+- exp/asr_stats_raw_en_char_ba_h2l4/train/text_shape.char
+valid_shape_file:
+- exp/asr_stats_raw_en_char_ba_h2l4/valid/speech_shape
+- exp/asr_stats_raw_en_char_ba_h2l4/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
+validate_each_iter_factory: true
+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_no_special_ba_h2l4/raw/train/wav.scp
+    - speech
+    - sound
+-   - dump_no_special_ba_h2l4/raw/train/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump_no_special_ba_h2l4/raw/dev/wav.scp
+    - speech
+    - sound
+-   - dump_no_special_ba_h2l4/raw/dev/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>
+- E
+- T
+- A
+- O
+- I
+- N
+- H
+- S
+- R
+- L
+- D
+- U
+- W
+- M
+- C
+- G
+- Y
+- B
+- P
+- F
+- K
+- ''''
+- V
+- X
+- J
+- Z
+- Q
+- ','
+- '-'
+- <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: 12
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d
+    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: {}
+masker: null
+masker_conf: {}
+required:
+- output_dir
+- token_list
+version: '202412'
+distributed: false

exp/asr_train_asr_lr002_raw_en_char_dur05_filter_ba_h2l4/valid.cer.ave_10best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bc682a914dd4c4f4b92a6f5f236d5ef67da32af8a0f8f530f983ab1c6fa73a2
+size 138927150

meta.yaml

@@ -0,0 +1,8 @@
+espnet: '202412'
+files:
+  asr_model_file: exp/asr_train_asr_lr002_raw_en_char_dur05_filter_ba_h2l4/valid.cer.ave_10best.pth
+python: 3.12.3 | packaged by Anaconda, Inc. | (main, May  6 2024, 19:46:43) [GCC 11.2.0]
+timestamp: 1756005458.084908
+torch: 2.4.0
+yaml_files:
+  asr_train_config: exp/asr_train_asr_lr002_raw_en_char_dur05_filter_ba_h2l4/config.yaml