Skip to page content

SAVRN

Explore the AI campus

Explore the operating platform

Learn about SAVRN

Search Plan a project

Independent publisher

Quan

wq2012

Audio and speech

Models in Library44

Datasets in Library0

Models on Hugging Face82

Followers4

Compare the published evidence

This profile connects the 40 model and dataset records shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.

Published tasks: Audio classification.

Reported licenses: apache-2.0. Open a record to review its specific license and conditions.

Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.

Models

Model · Audio classification

univ_conformer_small_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs) - modelfp32.tflite: Exported FP32 TensorFlow Lite model for edge/mobile CPU inference - modelint8.tflite: Dynamic-range INT8 quantized TensorFlow Lite model (~3.5x smaller)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

univ_lstm_small_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs) - modelfp32.tflite: Exported FP32 TensorFlow Lite model for edge/mobile CPU inference - modelint8.tflite: Dynamic-range INT8 quantized TensorFlow Lite model (~3.5x smaller)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

univ_ecapa_tdnn_small_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs) - modelfp32.tflite: Exported FP32 TensorFlow Lite model for edge/mobile CPU inference - modelint8.tflite: Dynamic-range INT8 quantized TensorFlow Lite model (~3.5x smaller)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

ls_lstm_small_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs) - modelfp32.tflite: Exported FP32 TensorFlow Lite model for edge/mobile CPU inference - modelint8.tflite: Dynamic-range INT8 quantized TensorFlow Lite model (~3.5x smaller)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

ls_conformer_small_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs) - modelfp32.tflite: Exported FP32 TensorFlow Lite model for edge/mobile CPU inference - modelint8.tflite: Dynamic-range INT8 quantized TensorFlow Lite model (~3.5x smaller)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

ls_ecapa_tdnn_small_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs) - modelfp32.tflite: Exported FP32 TensorFlow Lite model for edge/mobile CPU inference - modelint8.tflite: Dynamic-range INT8 quantized TensorFlow Lite model (~3.5x smaller)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

univ_conformer_tiny_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 693,124 parameters flaxspeaker

View model

Model · Audio classification

univ_conformer_small_dr_vectors

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

univ_conformer_small_arcface

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

cn_conformer_small_pfas

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

vox_ecapa_tdnn_small_ext_softmax

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

univ_transformer_small_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 1M parameters flaxspeaker

View model

Model · Audio classification

univ_mamba_small_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 1M parameters flaxspeaker

View model

Model · Audio classification

univ_ecapa_tdnn_tiny_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 626,720 parameters flaxspeaker

View model

Model · Audio classification

univ_ecapa_tdnn_base_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 3M parameters flaxspeaker

View model

Model · Audio classification

univ_conformer_small_pfas_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

univ_conformer_small_ext_softmax

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

univ_conformer_small_pfas

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

ls_resnet_small_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

ls_transformer_small_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 1M parameters flaxspeaker

View model

Model · Audio classification

ls_conformer_small_pfas_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

cn_conformer_small_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

ls_conformer_small_arcface

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

univ_resnet_small_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

univ_conformer_small_triplet

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

univ_conformer_small_sphereface

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

univ_conformer_small_cosface

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

ls_ecapa_tdnn_tiny_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 626,720 parameters flaxspeaker

View model

Model · Audio classification

ls_mamba_small_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 1M parameters flaxspeaker

View model

Model · Audio classification

ls_conformer_small_sphereface

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

ls_conformer_tiny_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 693,124 parameters flaxspeaker

View model

Model · Audio classification

cn_conformer_small_dr_vectors

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

cn_ecapa_tdnn_small_arcface

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

ls_conformer_small_cosface

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

ls_conformer_small_dr_vectors

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

univ_conformer_base_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 5M parameters flaxspeaker

View model

Model · Audio classification

ls_ecapa_tdnn_base_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 3M parameters flaxspeaker

View model

Model · Audio classification

ls_conformer_small_pfas

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

ls_conformer_small_triplet

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model

Model · Audio classification

vox_conformer_small_ge2e

model.safetensors: Primary model weights in SafeTensors format - flaxmodel.msgpack: Native Flax Msgpack serialized parameters - config.json: FlaxSpeakerConfig model & training architecture configuration - preprocessorconfig.json: WhisperFeatureExtractor-compatible frontend configuration - evalresults.json: Verified multi-domain evaluation metrics (1-utt & 3-utt EER, minDCF, ROC-AUC, 95% bootstrap CIs)

Open weights apache-2.0 2M parameters flaxspeaker

View model