Upload model from zenodo

README.md

@@ -0,0 +1,43 @@
+---
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+language: en
+datasets:
+- fsc_challenge
+license: cc-by-4.0
+---
+## ESPnet2 ASR pretrained model 
+### `siddhana/fsc_challenge_asr_train_asr_hubert_transformer_adam_specaug_raw_en_word_valid.acc.ave_5best`
+♻️ Imported from https://zenodo.org/record/5656007
+
+This model was trained by siddhana using fsc_challenge/asr1 recipe in [espnet](https://github.com/espnet/espnet/).
+### Demo: How to use in ESPnet2
+```python
+# coming soon
+```
+### 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 {Enrique Yalta Soplin} 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 Enrique Yalta Soplin 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_hubert_transformer_adam_specaug_raw_en_word/RESULTS.md

@@ -0,0 +1,31 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Sun Oct  3 22:25:25 EDT 2021`
+- python version: `3.8.11 (default, Aug  3 2021, 15:09:35)  [GCC 7.5.0]`
+- espnet version: `espnet 0.10.3a3`
+- pytorch version: `pytorch 1.9.0+cu102`
+- Git hash: `97b9dad4dbca71702cb7928a126ec45d96414a3f`
+  - Commit date: `Mon Sep 13 22:55:04 2021 +0900`
+
+## asr_train_asr_hubert_transformer_adam_specaug_raw_en_word
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_asr_model_valid.acc.ave_5best/spk_test|3349|17937|98.5|1.2|0.3|0.5|2.0|4.7|
+|inference_asr_model_valid.acc.ave_5best/utt_test|4204|22540|85.5|12.6|1.9|3.1|17.6|44.7|
+|inference_asr_model_valid.acc.ave_5best/valid|2597|13782|98.8|0.8|0.4|0.2|1.4|2.9|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|inference_asr_model_valid.acc.ave_5best/spk_test|3349|152191|99.2|0.5|0.3|0.3|1.1|4.7|
+|inference_asr_model_valid.acc.ave_5best/utt_test|4204|191435|92.4|5.3|2.3|2.7|10.3|44.7|
+|inference_asr_model_valid.acc.ave_5best/valid|2597|117282|99.4|0.4|0.3|0.2|0.8|2.9|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|

exp/asr_train_asr_hubert_transformer_adam_specaug_raw_en_word/config.yaml

@@ -0,0 +1,307 @@
+config: conf/tuning/train_asr_hubert_transformer_adam_specaug.yaml
+print_config: false
+log_level: INFO
+dry_run: false
+iterator_type: sequence
+output_dir: exp/asr_train_asr_hubert_transformer_adam_specaug_raw_en_word
+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: 80
+patience: null
+val_scheduler_criterion:
+- valid
+- loss
+early_stopping_criterion:
+- valid
+- loss
+- min
+best_model_criterion:
+-   - train
+    - loss
+    - min
+-   - valid
+    - loss
+    - min
+-   - train
+    - acc
+    - max
+-   - valid
+    - acc
+    - max
+keep_nbest_models: 5
+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_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: []
+num_iters_per_epoch: null
+batch_size: 20
+valid_batch_size: null
+batch_bins: 1000000
+valid_batch_bins: null
+train_shape_file:
+- exp/asr_stats_raw_en_word/train/speech_shape
+- exp/asr_stats_raw_en_word/train/text_shape.word
+valid_shape_file:
+- exp/asr_stats_raw_en_word/valid/speech_shape
+- exp/asr_stats_raw_en_word/valid/text_shape.word
+batch_type: folded
+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/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/valid/wav.scp
+    - speech
+    - sound
+-   - dump/raw/valid/text
+    - text
+    - text
+allow_variable_data_keys: false
+max_cache_size: 0.0
+max_cache_fd: 32
+valid_max_cache_size: null
+optim: adam
+optim_conf:
+    lr: 0.0002
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 25000
+token_list:
+- <blank>
+- <unk>
+- ▁the
+- ▁
+- e
+- ▁turn
+- ▁in
+- s
+- ▁lights
+- o
+- ▁m
+- c
+- i
+- ▁heat
+- a
+- t
+- hroom
+- ▁up
+- ▁s
+- ▁on
+- ▁down
+- n
+- ▁temperature
+- crease
+- p
+- ▁t
+- u
+- ▁b
+- ▁switch
+- w
+- h
+- d
+- ou
+- ▁kitchen
+- ▁volume
+- ▁off
+- ing
+- y
+- increase_volume_none
+- ▁bedroom
+- ▁langu
+- age
+- as
+- decrease_volume_none
+- ▁l
+- r
+- er
+- at
+- ▁d
+- l
+- decrease_heat_washroom
+- increase_heat_washroom
+- k
+- an
+- g
+- increase_heat_none
+- oo
+- decrease_heat_none
+- ge
+- change_language_none_none
+- activate_lights_washroom
+- activate_lights_kitchen
+- ow
+- in
+- activate_music_none
+- mp
+- deactivate_music_none
+- increase_heat_bedroom
+- increase_heat_kitchen
+- decrease_heat_kitchen
+- it
+- activate_lights_bedroom
+- deactivate_lights_bedroom
+- f
+- re
+- decrease_heat_bedroom
+- ed
+- deactivate_lights_kitchen
+- bring_newspaper_none
+- bring_shoes_none
+- bring_socks_none
+- activate_lights_none
+- deactivate_lights_none
+- q
+- deactivate_lights_washroom
+- change_language_Chinese_none
+- bring_juice_none
+- j
+- m
+- deactivate_lamp_none
+- activate_lamp_none
+- change_language_Korean_none
+- ▁k
+- me
+- change_language_German_none
+- ▁o
+- change_language_English_none
+- ▁he
+- ase
+- ff
+- ume
+- ▁v
+- x
+- ▁u
+- v
+- <sos/eos>
+init: null
+input_size: null
+ctc_conf:
+    dropout_rate: 0.0
+    ctc_type: builtin
+    reduce: true
+    ignore_nan_grad: true
+model_conf:
+    ctc_weight: 0.5
+    ignore_id: -1
+    lsm_weight: 0.0
+    length_normalized_loss: false
+    report_cer: true
+    report_wer: true
+    sym_space: <space>
+    sym_blank: <blank>
+    extract_feats_in_collect_stats: true
+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'
+frontend: s3prl
+frontend_conf:
+    frontend_conf:
+        upstream: hubert_large_ll60k
+    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: {}
+preencoder: linear
+preencoder_conf:
+    input_size: 1024
+    output_size: 80
+encoder: transformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 4
+    linear_units: 2048
+    num_blocks: 12
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.0
+    input_layer: conv2d
+    normalize_before: true
+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: 0.0
+    src_attention_dropout_rate: 0.0
+required:
+- output_dir
+- token_list
+version: 0.10.3a3
+distributed: false

exp/asr_train_asr_hubert_transformer_adam_specaug_raw_en_word/valid.acc.ave_5best.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29ee8265e7d7f4cc0ab13186cd45cf1713a8afa6b1a40683bae4fcfb82eabfb6
+size 1375817761

meta.yaml

@@ -0,0 +1,8 @@
+espnet: 0.10.3a3
+files:
+  asr_model_file: exp/asr_train_asr_hubert_transformer_adam_specaug_raw_en_word/valid.acc.ave_5best.pth
+python: "3.8.11 (default, Aug  3 2021, 15:09:35) \n[GCC 7.5.0]"
+timestamp: 1636435922.417136
+torch: 1.9.0+cu102
+yaml_files:
+  asr_train_config: exp/asr_train_asr_hubert_transformer_adam_specaug_raw_en_word/config.yaml