add files

README.md

@@ -0,0 +1,30 @@
+---
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+- speech-translation
+- language-identification
+language: multilingual
+datasets:
+- owsm_ctc_v4
+license: cc-by-4.0
+metrics:
+- cer
+- bleu
+- accuracy
+library_name: espnet
+---
+
+[OWSM-CTC](https://aclanthology.org/2024.acl-long.549/) (Peng et al., ACL 2024) is an encoder-only speech foundation model based on hierarchical multi-task self-conditioned CTC.
+OWSM-CTC v4 is trained on 320k hours of public audio data for multilingual speech recognition, any-to-any speech translation, and language identification, which follows the design of the project, [Open Whisper-style Speech Model (OWSM)](https://arxiv.org/abs/2401.16658).
+
+To use the pre-trained model, please install `espnet` and `espnet_model_zoo`. The requirements are:
+```
+librosa
+torch
+espnet
+espnet_model_zoo
+```
+
+**Example usage can be found in ESPnet:** https://github.com/espnet/espnet/tree/master/egs2/owsm_ctc_v3.1/s2t1

data/token_list/bpe_unigram50000/bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71278ea470760e4a9c903242cabda668a846307761c8b947976113970a394795
+size 1036703

exp/s2t_stats_raw_bpe50000/train/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00c22dba27594df8f1d8f74a491b20c6e6e8c17e92159f81dfd634f98c098654
+size 1786

exp/s2t_train_owsmctc_ebf27_conv2d8_size1024_mel128_bs320_raw_bpe50000/RESULTS.md

@@ -0,0 +1,9 @@
+<!-- Generated by scripts/utils/show_asr_result.sh -->
+# RESULTS
+## Environments
+- date: `Wed Jan 15 18:41:49 CST 2025`
+- python version: `3.11.8 | packaged by conda-forge | (main, Feb 16 2024, 20:38:00) [GCC 12.3.0]`
+- espnet version: `espnet 202412`
+- pytorch version: `pytorch 2.5.1`
+- Git hash: `447443550139bec75838b5a6dc654373c21079a0`
+  - Commit date: `Sun Jan 12 17:15:11 2025 -0600`

exp/s2t_train_owsmctc_ebf27_conv2d8_size1024_mel128_bs320_raw_bpe50000/valid.total_count.ave_5best.till70epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10f28cd40ee38582f68131f6502f306762183bf0e85fdc238ea401bd0e863ae4
+size 4045987222

meta.yaml

@@ -0,0 +1,8 @@
+espnet: '202310'
+files:
+  s2t_model_file: exp/s2t_train_owsmctc_ebf27_conv2d8_size1024_mel128_bs320_raw_bpe50000/valid.total_count.ave_5best.till70epoch.pth
+python: 3.12.2 | packaged by conda-forge | (main, Feb 16 2024, 20:38:53) [GCC 12.3.0]
+timestamp: 1737002738.816795
+torch: 2.5.1
+yaml_files:
+  s2t_train_config: exp/s2t_train_owsmctc_ebf27_conv2d8_size1024_mel128_bs320_raw_bpe50000/config.yaml