add model files

README.md

@@ -0,0 +1,15 @@
+---
+tags:
+- espnet
+- audio
+- automatic-speech-recognition
+- speech-translation
+- language-identification
+language: multilingual
+datasets:
+- owsm_v3.1_ctc
+license: cc-by-4.0
+---
+
+[OWSM-CTC](https://arxiv.org/abs/2402.12654) is an encoder-only speech foundation model based on multi-task self-conditioned CTC.
+It is trained on 180k hours of public audio data for multilingual speech recognition, any-to-any speech translation, and language identification, which follows the design of the previous [encoder-decoder OWSM](https://arxiv.org/abs/2401.16658).

data/token_list/bpe_unigram50000/bpe.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff9e37e2ec3b9c6cd1a2b02672b40a17b8bc2e11ad865a44518835a199dfd890
+size 1031801

exp/s2t_stats_raw_bpe50000/train/feats_stats.npz

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ef4b5e465110edf32eec024cf2427eedd677f5733bb87d6b2131e6984a6e13f
+size 1402

exp/s2t_train_s2t_multitask-ctc_ebf27_conv2d8_size1024_raw_bpe50000/valid.total_count.ave_5best.till40epoch.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e52260a1386c23a97d75d8dafaf6dccf1ac581dd3865ec9b2c0435b8f8102e3
+size 4020771173

meta.yaml

@@ -0,0 +1,8 @@
+espnet: '202310'
+files:
+  s2t_model_file: exp/s2t_train_s2t_multitask-ctc_ebf27_conv2d8_size1024_raw_bpe50000/valid.total_count.ave_5best.till40epoch.pth
+python: 3.10.13 | packaged by conda-forge | (main, Dec 23 2023, 15:36:39) [GCC 12.3.0]
+timestamp: 1708654076.994769
+torch: 1.13.1
+yaml_files:
+  s2t_train_config: exp/s2t_train_s2t_multitask-ctc_ebf27_conv2d8_size1024_raw_bpe50000/config.yaml