This repo contains the inference code to use pretrained human voice gender classifier. - You could also try Huggingface online demo. First, clone the original github repository and install the packages via pip. For those who need pretrained weights, please download it in here State-of-the-art speaker verification model already produces good representation of the speaker's gender. I used the pretrained ECAPA-TDNN from TaoRuijie's repository, added one linear layer to make two-class classifier, and finetuned the model with the VoxCeleb2 dev set. The model achieved 98.7% accuracy on the VoxCeleb1 identification test split. I would like to note the training dataset I've used for this model…
Open-weight model · Audio classification
distilhubert-finetuned-gtzan
by Rajesh Kumar imrajeshkr/distilhubert-finetuned-gtzan
This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset.
Parameters24M
Context—
Weights94.8 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads7
Runs On
What it takes to serve distilhubert-finetuned-gtzan (24M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.0 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
Model Card
By Rajesh Kumar, published under apache-2.0, revision f858f63e2b69.
This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set: - evalloss: 0.8970 - evalmodelpreparationtime: 0.0018 - evalaccuracy: 0.87 - evalruntime: 443.4759 - evalsamplespersecond: 0.225 - evalstepspersecond: 0.029 The following hyperparameters were used during training: - learningrate: 5e-05 - trainbatchsize: 8 - evalbatchsize: 8 - lrschedulertype: linear - lrschedulerwarmupsteps: 100 - numepochs: 10 - mixedprecisiontraining: Native AMP - labelsmoothingfactor: 0.1 - Transformers 5.16.1 - Pytorch 2.11.0+cpu - Datasets 2.19.0 - Tokenizers 0.23.1
Read Rajesh Kumar's full model card
This model is a fine-tuned version of ntu-spml/distilhubert on the GTZAN dataset. It achieves the following results on the evaluation set: - eval_loss: 0.8970 - eval_model_preparation_time: 0.0018 - eval_accuracy: 0.87 - eval_runtime: 443.4759 - eval_samples_per_second: 0.225 - eval_steps_per_second: 0.029 - epoch: 0 - step: 0
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 8 - eval_batch_size: 8 - seed: 42 - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments - lr_scheduler_type: linear - lr_scheduler_warmup_steps: 100 - num_epochs: 10 - mixed_precision_training: Native AMP - label_smoothing_factor: 0.1
Framework versions
- Transformers 5.16.1
- Pytorch 2.11.0+cpu
- Datasets 2.19.0
- Tokenizers 0.23.1
Configuration
- Architecture
- HubertForSequenceClassification
- Layers
- 2
- Hidden size
- 768
- Feed-forward size
- 3,072
- Attention heads
- 12
- Vocabulary size
- 32
- Model type
- hubert
Identity and Version
- Repository
- imrajeshkr/distilhubert-finetuned-gtzan
- Publisher
- Rajesh Kumar
- Task
- Audio classification
- Modality
- Audio
- Library
- transformers
- Parameters
- 24M parameters
- Languages
- Not stated by the source
- Revision
- f858f63e2b69beb4e601dda774ef86c37e20b963
- First published
- 2024-04-29
- Last updated
- 2026-09-18
Files and Weights
8 files, 94.8 MB in total. The weights are 2 files totalling 94.8 MB in bin, safetensors.
Weights2 files · 94.8 MB
Configuration2 files · 2.1 KB
Documentation1 file · 1.6 KB
Other2 files · 14.3 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 94.8 MB | 2b3201d967ae |
| training_args.bin | Weights | 5.2 KB | f7e872332e2f |
| config.json | Configuration | 1.9 KB | — |
| preprocessor_config.json | Configuration | 212 B | — |
| README.md | Documentation | 1.6 KB | — |
| runs/Apr29_19-16-03_6a83ad1054b9/events.out.tfevents.1714418171.6a83ad1054b9.9960.0 | Other | 13.9 KB | e5989702a863 |
| runs/Apr29_19-16-03_6a83ad1054b9/events.out.tfevents.1714419394.6a83ad1054b9.9960.1 | Other | 405 B | 0aa55afdc3ec |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 94.8 MB
Download from Rajesh Kumar
Released by Rajesh Kumar through its official repository on Hugging Face. Read the license.
Built From
- Derived from ntu-spml/distilhubert
- Trained on (disclosed) marsyas/gtzan
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 94.8 MB |
| 16-bit | 0.0 GB |
| 8-bit | 0.0 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About distilhubert-finetuned-gtzan
How much GPU memory does distilhubert-finetuned-gtzan need?
About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (24M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run distilhubert-finetuned-gtzan on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use distilhubert-finetuned-gtzan commercially?
Yes. distilhubert-finetuned-gtzan is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
CED are simple ViT-Transformer-based models for audio tagging, achieving sota performance on Audioset. Notable differences from other available models include: 1. Simplification for finetuning: Batchnormalization of Mel-Spectrograms. During finetuning one does not need to first compute mean/variance over the dataset, which is common for AST. 1. Support for variable length inputs. Most other models use a static time-frequency position embedding, which hinders the model's generalization to segments shorter than 10s. Many previous transformers simply pad their input to 10s in order to avoid the performance impact, which in turn slows down training/inference drastically. 1. Training/Inference…
DistilWav2Vec2 Adult/Child Speech Classifier is an audio classification model based on the wav2vec 2.0 architecture. This model is a distilled version of wav2vec2-adult-child-cls on a private adult/child speech classification dataset. This model was trained using HuggingFace's PyTorch framework. All training was done on a Tesla P100, provided by Kaggle. Training metrics were logged via Tensorboard. The model achieves the following results on evaluation: The following hyperparameters were used during training: - learningrate: 3e-05 - trainbatchsize: 32 - evalbatchsize: 32 - seed: 42 - gradientaccumulationsteps: 4 - totaltrainbatchsize: 128 - optimizer: Adam with betas=(0.9,0.999) and…
MLX-compatible weights for WeSpeaker ResNet34-LM, converted from the pyannote speaker embedding model with BatchNorm fused into Conv2d. WeSpeaker ResNet34-LM is a speaker embedding model (~6.6M params) that produces 256-dimensional L2-normalized speaker embeddings from audio. Trained on VoxCeleb for speaker verification and diarization. BatchNorm is fused into Conv2d at conversion time — no BN layers in the MLX model. Part of speech-swift. Converts the original pyannote/wespeaker-voxceleb-resnet34-LM checkpoint using a custom unpickler (no pyannote.audio dependency required). Key transformations: - Fuse BatchNorm into Conv2d: wfused = w × γ/√(σ²+ε), bfused = β − μ×γ/√(σ²+ε) - Transpose…
MLX port of snakers4/silero-vad tag v6.2.1 for voice activity detection on Apple Silicon. Measured with speech-swift release tests on Apple Silicon using a 20 s 16 kHz speech fixture, 625 streaming chunks. Parity against the matching CoreML v6.2.1 export: The exported safetensors were also checked tensor-by-tensor against the upstream v6.2.1 JIT state dict after conversion; the maximum absolute tensor difference was 0. Converted from snakers4/silero-vad tag v6.2.1. The upstream project is MIT licensed. - speech-swift - Apple SDK - Docs - install and CLI docs - soniqo.audio - website - blog - blog
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…