Duplicate from ShandaAI/AudioSep-hive

.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 +1,33 @@
+---
+license: apache-2.0
+language:
+- en
+tags:
+- audio
+- sound-separation
+- audio-to-audio
+- audiosep
+datasets:
+- ShandaAI/Hive
+---
+
+# AudioSep-hive
+
+## Model Description
+
+**AudioSep-hive** is a data-efficient, query-based universal sound separation model trained on the [Hive dataset](https://huggingface.co/datasets/ShandaAI/Hive). By leveraging the high-quality, semantically consistent Hive dataset, this model achieves competitive separation accuracy and perceptual quality comparable to state-of-the-art models (such as SAM-Audio) while utilizing only a fraction (~0.2%) of the training data volume.
+
+This model is developed by **Shanda AI Research Tokyo** and is introduced in the paper: [A Semantically Consistent Dataset for Data-Efficient Query-Based Universal Sound Separation](https://arxiv.org/abs/2601.22599).
+
+## Model Details
+
+- **Model Type:​** Query-Based Universal Sound Separation
+- **Language(s):​** English (for text queries)
+- **License:​** Apache 2.0 (Please update if different)
+- **Trained on:​** [ShandaAI/Hive](https://huggingface.co/datasets/ShandaAI/Hive) (2,442 hours of raw audio, 19.6M mixtures)
+- **Paper:​** [arXiv:2601.22599](https://arxiv.org/abs/2601.22599)
+- **Code Repository:​** [GitHub - ShandaAI/Hive](https://github.com/ShandaAI/Hive)
+
+## Uses
+
+The model is intended for universal sound separation tasks, allowing users to extract specific sounds from complex audio mixtures using multimodal prompts (e.g., text descriptions or audio queries). 

audiosep_hive.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a13fff5fa4ece1a8bc13e42e1c7b8d90e21603075302ca89e4339c9471973300
+size 1264846755

config.yaml

@@ -0,0 +1,42 @@
+---
+task_name: AudioSep
+
+data:
+    datafiles:
+        - 'datafiles/template.json'
+
+    sampling_rate: 32000
+    segment_seconds: 5
+    loudness_norm:
+        lower_db: -10
+        higher_db: 10
+    max_mix_num: 2
+
+model:
+    query_net: CLAP
+    condition_size: 512
+    model_type: ResUNet30
+    input_channels: 1
+    output_channels: 1
+    resume_checkpoint: ""
+    use_text_ratio: 1.0
+
+train:
+    optimizer:
+        optimizer_type: AdamW
+        learning_rate: 1e-3
+        warm_up_steps: 10000
+        reduce_lr_steps: 1000000
+        lr_lambda_type: constant_warm_up
+    num_nodes: 1
+    num_workers: 6
+    loss_type: l1_wav
+    sync_batchnorm: True
+    batch_size_per_device: 12
+    steps_per_epoch: 10000
+    evaluate_step_frequency: 10000
+    save_step_frequency: 20000
+    early_stop_steps: 10000001
+    random_seed: 1234
+
+

music_speech_audioset_epoch_15_esc_89.98.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c68f12f9d7ea25fdaaccf741ec7f81e93ee594455410f3bca4f47f88d8e006
+size 2352471003