Upload 4 files

README.md

@@ -0,0 +1,90 @@
+---
+license: cc-by-4.0
+language:
+- en
+pipeline_tag: summarization
+tags:
+- speaker embedding
+- wespeaker
+- speaker modelling
+---
+
+
+Official model provided by [Wespeaker](https://github.com/wenet-e2e/wespeaker) project, ResNet293 based r-vector (After large margin finetune)
+
+The model is trained on VoxCeleb2 Dev dataset, containing 5994 speakers.
+
+## Model Sources
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** https://github.com/wenet-e2e/wespeaker
+- **Paper:** https://arxiv.org/pdf/2210.17016.pdf
+- **Demo:** https://huggingface.co/spaces/wenet/wespeaker_demo
+
+
+## Results on VoxCeleb
+| Model | Params | Flops | LM | AS-Norm | vox1-O-clean | vox1-E-clean | vox1-H-clean |
+|:------|:------:|:------|:--:|:-------:|:------------:|:------------:|:------------:|
+| ResNet293-TSTP-emb256 | 28.62M | 28.10G | × | × | 0.595 | 0.756 | 1.433 |
+|                       |        |        | × | √ | 0.537 | 0.701 | 1.276 |
+|                       |        |        | √ | × | 0.532 | 0.707 | 1.311 |
+|                       |        |        | √ | √ | **0.447** | **0.657** | **1.183** |
+
+## Install Wespeaker
+
+``` sh
+pip install git+https://github.com/wenet-e2e/wespeaker.git
+```
+
+for development install:
+
+``` sh
+git clone https://github.com/wenet-e2e/wespeaker.git
+cd wespeaker
+pip install -e .
+```
+
+
+### Command line Usage
+
+``` sh
+$ wespeaker -p resnet293_download_dir --task embedding --audio_file audio.wav --output_file embedding.txt
+$ wespeaker -p resnet293_download_dir --task embedding_kaldi --wav_scp wav.scp --output_file /path/to/embedding
+$ wespeaker -p resnet293_download_dir --task similarity --audio_file audio.wav --audio_file2 audio2.wav
+$ wespeaker -p resnet293_download_dir --task diarization --audio_file audio.wav
+```
+
+### Python Programming Usage
+
+``` python
+import wespeaker
+
+model = wespeaker.load_model_local(resnet293_download_dir)
+# set_gpu to enable the cuda inference, number < 0 means using CPU
+model.set_gpu(0)
+
+# embedding/embedding_kaldi/similarity/diarization
+embedding = model.extract_embedding('audio.wav')
+utt_names, embeddings = model.extract_embedding_list('wav.scp')
+similarity = model.compute_similarity('audio1.wav', 'audio2.wav')
+diar_result = model.diarize('audio.wav')
+
+# register and recognize
+model.register('spk1', 'spk1_audio1.wav')
+model.register('spk2', 'spk2_audio1.wav')
+model.register('spk3', 'spk3_audio1.wav')
+result = model.recognize('spk1_audio2.wav')
+```
+
+## Citation
+```bibtex
+@inproceedings{wang2023wespeaker,
+  title={Wespeaker: A research and production oriented speaker embedding learning toolkit},
+  author={Wang, Hongji and Liang, Chengdong and Wang, Shuai and Chen, Zhengyang and Zhang, Binbin and Xiang, Xu and Deng, Yanlei and Qian, Yanmin},
+  booktitle={IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
+  pages={1--5},
+  year={2023},
+  organization={IEEE}
+}
+```

avg_model.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7b8447ea84345e26432461b4dda224d1af34a3985a438268e0dfbbde059b1ce
+size 133998630

config.yaml

@@ -0,0 +1,78 @@
+data_type: shard
+dataloader_args:
+  batch_size: 32
+  drop_last: true
+  num_workers: 16
+  pin_memory: false
+  prefetch_factor: 8
+dataset_args:
+  aug_prob: 0.6
+  fbank_args:
+    dither: 1.0
+    frame_length: 25
+    frame_shift: 10
+    num_mel_bins: 80
+  num_frms: 200
+  shuffle: true
+  shuffle_args:
+    shuffle_size: 2500
+  spec_aug: false
+  spec_aug_args:
+    max_f: 8
+    max_t: 10
+    num_f_mask: 1
+    num_t_mask: 1
+    prob: 0.6
+  speed_perturb: true
+exp_dir: exp/ResNet293-TSTP-emb256-fbank80-num_frms200-aug0.6-spTrue-saFalse-ArcMargin-SGD-epoch150
+gpus:
+- 0
+- 1
+log_batch_interval: 100
+loss: CrossEntropyLoss
+loss_args: {}
+margin_scheduler: MarginScheduler
+margin_update:
+  epoch_iter: 17062
+  final_margin: 0.2
+  fix_start_epoch: 40
+  increase_start_epoch: 20
+  increase_type: exp
+  initial_margin: 0.0
+  update_margin: true
+model: ResNet293
+model_args:
+  embed_dim: 256
+  feat_dim: 80
+  pooling_func: TSTP
+  two_emb_layer: false
+model_init: null
+noise_data: data/musan/lmdb
+num_avg: 2
+num_epochs: 150
+optimizer: SGD
+optimizer_args:
+  lr: 0.1
+  momentum: 0.9
+  nesterov: true
+  weight_decay: 0.0001
+projection_args:
+  easy_margin: false
+  embed_dim: 256
+  num_class: 17982
+  project_type: arc_margin
+  scale: 32.0
+reverb_data: data/rirs/lmdb
+save_epoch_interval: 5
+scheduler: ExponentialDecrease
+scheduler_args:
+  epoch_iter: 17062
+  final_lr: 5.0e-05
+  initial_lr: 0.1
+  num_epochs: 150
+  scale_ratio: 1.0
+  warm_from_zero: true
+  warm_up_epoch: 6
+seed: 42
+train_data: data/vox2_dev/shard.list
+train_label: data/vox2_dev/utt2spk

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb1ccc7754caff552ebc46347a51aaee2669bb24efc740e665d1a1133d20e98
+size 114336285