upload model

README.md

@@ -0,0 +1,73 @@
+---
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+language: iba
+datasets:
+- Iban
+license: cc-by-4.0
+---
+
+## ESPnet2 ASR model
+
+### `cjli/cjli_wavlm_transformer`
+
+This model was trained using iban recipe in [espnet](https://github.com/espnet/espnet/).
+
+### Run recipe
+
+Follow the [ESPnet installation instructions](https://espnet.github.io/espnet/installation.html) first, then:
+
+```bash
+cd espnet/egs2/iban/asr1
+./run.sh --skip_data_prep false --skip_train true --download_model cjli/iban_wavlm_transformer
+```
+
+### Results
+
+**WER**
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.best/test|104|2226|71.2|23.8|5.1|2.3|31.2|94.2|
+
+**CER**
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.best/test|104|13527|91.8|2.7|5.4|2.2|10.4|94.2|
+
+**TER**
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.best/test|104|5758|81.2|10.9|7.8|2.7|21.4|94.2|
+
+
+### 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}
+}
+```

data/iba_token_list/bpe_unigram200/bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:007bb1faf4ba4576137adc53b3480c937b9f3a713873417288e8b667735ba572
+size 240535

exp/asr_train_asr_wavlm_conformer_raw_iba_bpe200_sp/28epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0caf7589588e72d28ad9d07b00b6298751c7faa4660b0e23c5796896f84c6363
+size 1384762787

exp/asr_train_asr_wavlm_conformer_raw_iba_bpe200_sp/RESULTS.md

@@ -0,0 +1,49 @@
+[INFO] /jet/home/cli22/ocean/my-espnet/egs2/iban/asr1/../../../tools/activate_python.sh is not present
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Mon May 12 12:37:16 EDT 2025`
+- python version: `3.10.13 | packaged by conda-forge | (main, Dec 23 2023, 15:36:39) [GCC 12.3.0]`
+- espnet version: `espnet 202412`
+- pytorch version: `pytorch 2.0.1`
+- Git hash: `9e12b0c877d28fba8ae1ce71abf6ed91c05d9238`
+  - Commit date: `Tue May 6 07:28:58 2025 -0400`
+
+## exp/asr_train_asr_wavlm_conformer_raw_iba_bpe200_sp
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.best/test|104|2226|71.2|23.8|5.1|2.3|31.2|94.2|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.best/test|104|13527|91.8|2.7|5.4|2.2|10.4|94.2|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|decode_asr_asr_model_valid.acc.best/test|104|5758|81.2|10.9|7.8|2.7|21.4|94.2|
+
+## exp/asr_train_asr_wavlm_conformer_raw_iba_bpe200_sp/decode_asr_asr_model_valid.acc.best
+### WER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/dev|473|11006|80.0|16.4|3.5|2.4|22.3|92.0|
+
+### CER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/dev|473|67025|94.9|1.9|3.3|1.7|6.9|92.0|
+
+### TER
+
+|dataset|Snt|Wrd|Corr|Sub|Del|Ins|Err|S.Err|
+|---|---|---|---|---|---|---|---|---|
+|org/dev|473|27176|87.7|7.5|4.8|1.9|14.2|92.0|
+

exp/asr_train_asr_wavlm_conformer_raw_iba_bpe200_sp/config.yaml

@@ -0,0 +1,431 @@
+config: conf/tuning/train_asr_wavlm_conformer.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_wavlm_conformer_raw_iba_bpe200_sp
+ngpu: 1
+seed: 2025
+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
+use_deepspeed: false
+deepspeed_config: null
+gradient_as_bucket_view: true
+ddp_comm_hook: null
+cudnn_enabled: true
+cudnn_benchmark: false
+cudnn_deterministic: true
+use_tf32: false
+collect_stats: false
+write_collected_feats: false
+max_epoch: 30
+patience: null
+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: 3
+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_adapter: false
+adapter: lora
+save_strategy: all
+adapter_conf: {}
+pretrain_path: null
+init_param: []
+ignore_init_mismatch: false
+freeze_param:
+- frontend.upstream
+num_iters_per_epoch: null
+batch_size: 20
+valid_batch_size: null
+batch_bins: 1600000
+valid_batch_bins: null
+category_sample_size: 10
+train_shape_file:
+- exp/asr_stats_raw_iba_bpe200_sp/train/speech_shape
+- exp/asr_stats_raw_iba_bpe200_sp/train/text_shape.bpe
+valid_shape_file:
+- exp/asr_stats_raw_iba_bpe200_sp/valid/speech_shape
+- exp/asr_stats_raw_iba_bpe200_sp/valid/text_shape.bpe
+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/raw/train_sp/wav.scp
+    - speech
+    - sound
+-   - dump/raw/train_sp/text
+    - text
+    - text
+valid_data_path_and_name_and_type:
+-   - dump/raw/dev/wav.scp
+    - speech
+    - sound
+-   - dump/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: 0.005
+scheduler: warmuplr
+scheduler_conf:
+    warmup_steps: 15000
+token_list:
+- <blank>
+- <unk>
+- ▁
+- i
+- u
+- ka
+- a
+- k
+- t
+- e
+- m
+- l
+- h
+- p
+- s
+- ▁ke
+- b
+- r
+- ▁di
+- o
+- an
+- ▁tu
+- ng
+- ▁s
+- ▁ti
+- ▁be
+- la
+- ▁p
+- in
+- ang
+- ta
+- ▁ba
+- ▁enggau
+- ▁nya
+- ▁n
+- g
+- er
+- ja
+- ▁se
+- ri
+- ku
+- n
+- ▁d
+- ▁ari
+- ra
+- ▁m
+- ▁menua
+- y
+- ar
+- d
+- ▁iya
+- ▁madah
+- di
+- ah
+- en
+- ▁deka
+- ▁a
+- ti
+- j
+- ▁b
+- ▁pengawa
+- it
+- c
+- ▁pe
+- ai
+- ga
+- lan
+- ▁ma
+- ung
+- ▁peng
+- alam
+- un
+- am
+- ▁udah
+- sa
+- ▁k
+- ▁menteri
+- ▁orang
+- da
+- ur
+- ▁sida
+- ▁ngagai
+- si
+- al
+- ▁datu
+- ▁ng
+- w
+- ▁puluh
+- ▁pen
+- ▁berita
+- ▁dua
+- ma
+- ▁ka
+- ▁enda
+- ▁nga
+- ▁pem
+- re
+- at
+- ▁na
+- ▁malaysia
+- ▁nge
+- ntu
+- ▁c
+- du
+- ▁l
+- ▁agi
+- ▁kena
+- 'on'
+- ▁perintah
+- ▁me
+- nya
+- mba
+- ▁tau
+- f
+- ▁opis
+- ▁te
+- ▁sarawak
+- ▁diatu
+- ▁nyadi
+- ratus
+- ▁mayuh
+- ad
+- ▁besai
+- ▁tiga
+- ▁lalu
+- aya
+- ▁seri
+- ▁g
+- ▁jaku
+- ▁bis
+- ▁ulih
+- ▁satu
+- ▁bala
+- ▁taun
+- ▁lima
+- ▁mega
+- ▁bansa
+- ▁pengerami
+- ▁raban
+- ▁ribu
+- ▁kuching
+- ▁mansut
+- ▁empat
+- v
+- ereta
+- ▁ngena
+- ▁ju
+- ▁gawa
+- ▁enam
+- manah
+- ▁hari
+- ▁penya
+- ▁patut
+- ▁tadi
+- ▁dikena
+- ▁pekara
+- ▁belas
+- ▁baru
+- asal
+- ▁lebuh
+- ▁lapan
+- ▁nembiak
+- ▁tujuh
+- ▁semua
+- ▁ringgit
+- ▁endur
+- aji
+- ▁atur
+- ▁pemansang
+- ▁mensia
+- ▁penemu
+- ▁gerempung
+- guna
+- ereja
+- ▁projek
+- ▁ngambi
+- ▁rakyat
+- ▁rayat
+- ▁kemari
+- ▁bengkah
+- ▁progr
+- ▁abdul
+- ▁dagang
+- ▁pelajar
+- erima
+- ▁waifm
+- ▁pengara
+- ▁nitih
+- ▁nasional
+- ▁bejalai
+- ▁laban
+- ▁bendar
+- ▁dayak
+- ▁sembi
+- z
+- '-'
+- x
+- '2'
+- 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: bpe
+bpemodel: data/iba_token_list/bpe_unigram200/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'
+short_noise_thres: 0.5
+aux_ctc_tasks: []
+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: 0.3
+    lsm_weight: 0.1
+    length_normalized_loss: false
+    extract_feats_in_collect_stats: false
+preencoder: linear
+preencoder_conf:
+    input_size: 1024
+    output_size: 80
+encoder: conformer
+encoder_conf:
+    output_size: 256
+    attention_heads: 4
+    linear_units: 1024
+    num_blocks: 12
+    dropout_rate: 0.1
+    positional_dropout_rate: 0.1
+    attention_dropout_rate: 0.1
+    input_layer: conv2d
+    normalize_before: true
+    macaron_style: true
+    rel_pos_type: latest
+    pos_enc_layer_type: rel_pos
+    selfattention_layer_type: rel_selfattn
+    activation_type: swish
+    use_cnn_module: true
+    cnn_module_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
+preprocessor: default
+preprocessor_conf: {}
+required:
+- output_dir
+- token_list
+version: '202412'
+distributed: false

meta.yaml

@@ -0,0 +1,8 @@
+espnet: '202412'
+files:
+  asr_model_file: exp/asr_train_asr_wavlm_conformer_raw_iba_bpe200_sp/28epoch.pth
+python: 3.10.13 | packaged by conda-forge | (main, Dec 23 2023, 15:36:39) [GCC 12.3.0]
+timestamp: 1747077768.065848
+torch: 2.0.1
+yaml_files:
+  asr_train_config: exp/asr_train_asr_wavlm_conformer_raw_iba_bpe200_sp/config.yaml