GGUF quantizations of the CED family (Consistent Ensemble Distillation, Xiaomi) - SOTA-tier audio-tagging models that classify everyday sounds (baby cry, footsteps, glass breaking, alarms, dog bark,...) into the 527-class AudioSet ontology. These files run with ced.cpp, a standalone C++/ggml port (no Python, no PyTorch at inference), and with LocalAI via the ced backend. Converted from the mispeech/ced- checkpoints (Apache-2.0). CED is a plain AST/DeiT Vision Transformer over a log-mel spectrogram; the port is numerically equal to the PyTorch reference. One self-contained GGUF per size + quant (config, 527 labels, and the mel filterbank/window are all embedded). Pick by your accuracy/size…
Open-weight model · Audio classification
ast-finetuned-audioset-10-10-0.4593
by Joshua Xenova/ast-finetuned-audioset-10-10-0.4593
https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593 with ONNX weights to be compatible with Transformers.js.
Parameters—
Context—
Weights867.5 MB
License—
AccessOpen weights
Monthly Downloads17.8k
Model Card
https://huggingface.co/MIT/ast-finetuned-audioset-10-10-0.4593 with ONNX weights to be compatible with Transformers.js. If you haven't already, you can install the Transformers.js JavaScript library from NPM using: Example: Perform audio classification with Xenova/ast-finetuned-audioset-10-10-0.4593 and return top 4 results. Note: Having a separate repo for ONNX weights is intended to be a temporary solution until WebML gains more traction. If you would like to make your models web-ready, we recommend converting to ONNX using Optimum and structuring your repo like this one (with ONNX weights located in a subfolder named onnx).
Excerpt from the card by Joshua.
Configuration
- Architecture
- ASTForAudioClassification
- Layers
- 12
- Hidden size
- 768
- Feed-forward size
- 3,072
- Attention heads
- 12
- Model type
- audio-spectrogram-transformer
Identity and Version
- Repository
- Xenova/ast-finetuned-audioset-10-10-0.4593
- Publisher
- Joshua
- Task
- Audio classification
- Modality
- Audio
- Library
- transformers.js
- Parameters
- Not stated by the source
- Languages
- Not stated by the source
- Revision
- 249a1fbf0286b40e7f1ed687a8ae396997bf7dc6
- First published
- 2023-06-27
- Last updated
- 2025-06-27
Files and Weights
13 files, 867.5 MB in total. The weights are 7 files totalling 867.5 MB in onnx.
Weights7 files · 867.5 MB
Configuration4 files · 28.7 KB
Documentation1 file · 1.6 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| onnx/model.onnx | Weights | 346.8 MB | 6ff353b1e809 |
| onnx/model_bnb4.onnx | Weights | 54.7 MB | b0125fb2d405 |
| onnx/model_fp16.onnx | Weights | 173.7 MB | 5f41fdc5b945 |
| onnx/model_q4.onnx | Weights | 60.0 MB | 20f3205b130b |
| onnx/model_q4f16.onnx | Weights | 51.4 MB | 93dda91efb2b |
| onnx/model_quantized.onnx | Weights | 90.8 MB | 807d244b58a3 |
| onnx/model_uint8.onnx | Weights | 90.2 MB | 870d92676e4d |
| config.json | Configuration | 26.8 KB | — |
| preprocessor_config.json | Configuration | 297 B | — |
| quant_config.json | Configuration | 810 B | — |
| quantize_config.json | Configuration | 810 B | — |
| README.md | Documentation | 1.6 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 867.5 MB
Download from Joshua
Released by Joshua through its official repository on Hugging Face.
Built From
- Derived from MIT/ast-finetuned-audioset-10-10-0.4593
- Quantized from MIT/ast-finetuned-audioset-10-10-0.4593
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 867.5 MB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Similar Models
This is a spoken language recognition model trained on the VoxLingua107 dataset using SpeechBrain. The model uses the ECAPA-TDNN architecture that has previously been used for speaker recognition. However, it uses more fully connected hidden layers after the embedding layer, and cross-entropy loss was used for training. We observed that this improved the performance of extracted utterance embeddings for downstream tasks. The system is trained with recordings sampled at 16kHz (single channel). The code will automatically normalize your audio (i.e., resampling + mono channel selection) when calling classifyfile if needed. The model can classify a speech utterance according to the language…
Abstract: The recognition of accented speech still remains a dominant problem in Automatic Speech Recognition (ASR) systems. We approach the classification of accented English speech through the Emphasized Channel Attention, Propagation and Aggregation Time Delay Neural Network (ECAPA-TDNN) architecture which has been shown to perform well on a variety of speech tasks. Three models are proposed: one trained from scratch, another two models (one using data augmentation and a baseline model) fine-tuned from the checkpoints of speechbrain/spkrec-ecapa-voxceleb (VoxCeleb). Our results show that the model fine-tuned with data augmentation yield the best results. Most of the misclassifications…
The development log of our Music Audio Pre-training (m-a-p) model family: - 02/06/2023: arxiv pre-print and training codes released. - 17/03/2023: we release two advanced music understanding models, MERT-v1-95M and MERT-v1-330M, trained with new paradigm and dataset. They outperform the previous models and can better generalize to more tasks. - 14/03/2023: we retrained the MERT-v0 model with open-source-only music dataset MERT-v0-public - 29/12/2022: a music understanding model MERT-v0 trained with MLM paradigm, which performs better at downstream tasks. - 29/10/2022: a pre-trained MIR model music2vec trained with BYOL paradigm. Here is a table for quick model pick-up: The m-a-p models…
The development log of our Music Audio Pre-training (m-a-p) model family: - 02/06/2023: arxiv pre-print and training codes released. - 17/03/2023: we release two advanced music understanding models, MERT-v1-95M and MERT-v1-330M, trained with new paradigm and dataset. They outperform the previous models and can better generalize to more tasks. - 14/03/2023: we retrained the MERT-v0 model with open-source-only music dataset MERT-v0-public - 29/12/2022: a music understanding model MERT-v0 trained with MLM paradigm, which performs better at downstream tasks. - 29/10/2022: a pre-trained MIR model music2vec trained with BYOL paradigm. Here is a table for quick model pick-up: The m-a-p models…
This model combines the SpeechBrain ECAPA-TDNN speaker embedding model with an SVM classifier to predict speaker gender from audio input. The model was trained and evaluated on the VoxCeleb2, Mozilla Common Voice v10.0, and TIMIT datasets - Mozilla Common Voice v10.0 English validated test set: 92.3% accuracy The model was trained on VoxCeleb2 dataset: - Converted to WAV format, single channel, 16kHz sampling rate, 256 kp/s bitrate - Applied SileroVAD for voice activity detection, taking the first voiced segment You can install the package directly from GitHub: - Model was trained on celebrity voices from YouTube interviews - Performance may vary on different audio qualities or recording…