Duplicate from reazon-research/japanese-hubert-base-k2

Co-authored-by: Yuta Sasaki <yubo0306@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+language: ja
+datasets: reazon-research/reazonspeech
+pipeline_tag: feature-extraction
+tags:
+- hubert
+- speech
+- k2ssl
+license: apache-2.0
+---
+
+# `reazon-research/japanese-hubert-base-k2`
+
+This is a Japanese Hubert Base model pre-trained on [ReazonSpeech v2.0 corpus](https://huggingface.co/datasets/reazon-research/reazonspeech) using the k2 framework.
+
+This model is converted from the k2 model.
+
+We also release the CTC models, [`reazon-research/japanese-hubert-base-k2-rs35kh`](https://huggingface.co/reazon-research/japanese-hubert-base-k2-rs35kh) and [`reazon-research/japanese-hubert-base-k2-rs35kh-bpe`](https://huggingface.co/reazon-research/japanese-hubert-base-k2-rs35kh-bpe), derived from this model.
+
+## Usage
+
+```python
+import librosa
+import torch
+from transformers import AutoFeatureExtractor, AutoModel
+
+feature_extractor = AutoFeatureExtractor.from_pretrained("reazon-research/japanese-hubert-base-k2")
+model = AutoModel.from_pretrained("reazon-research/japanese-hubert-base-k2")
+
+audio, sr = librosa.load(audio_file, sr=16_000)
+inputs = feature_extractor(
+    audio,
+    return_tensors="pt",
+    sampling_rate=sr,
+)
+with torch.inference_mode():
+    outputs = model(**inputs)
+```
+
+## Citation
+
+```bibtex
+@misc{reazon-research-japanese-hubert-base-k2,
+  title={japanese-hubert-base-k2},
+  author={Sasaki, Yuta},
+  url = {https://huggingface.co/reazon-research/japanese-hubert-base-k2},
+  year = {2025}
+}
+
+@article{yang2024k2ssl,
+  title={k2SSL: A faster and better framework for self-supervised speech representation learning},
+  author={Yang, Yifan and Zhuo, Jianheng and Jin, Zengrui and Ma, Ziyang and Yang, Xiaoyu and Yao, Zengwei and Guo, Liyong and Kang, Wei and Kuang, Fangjun and Lin, Long and others},
+  journal={arXiv preprint arXiv:2411.17100},
+  year={2024}
+}
+```
+
+## License
+
+[Apache Licence 2.0](https://choosealicense.com/licenses/apache-2.0/)

config.json

@@ -0,0 +1,72 @@
+{
+  "activation_dropout": 0.1,
+  "apply_spec_augment": true,
+  "architectures": [
+    "HubertModel"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_pos_batch_norm": false,
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "do_stable_layer_norm": false,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.0,
+  "feat_proj_layer_norm": true,
+  "final_dropout": 0.1,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.1,
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_prob": 0.05,
+  "model_type": "hubert",
+  "num_attention_heads": 12,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "transformers_version": "4.56.0",
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:342e0d687c5448da900134a8d682c512ffb3da2c80819e8cc2f9e22c0fe5e864
+size 377510632

preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}