smkrv/speech-emotion-classification-onnx
By smkrv · ↓ 0 · ♥ 1 · Updated 2026-02-27
What's in this repo
This page lists the files in smkrv/speech-emotion-classification-onnx, including model.onnx, model_bnb4.onnx, model_fp16.onnx and more.
- 8 ONNX models (.onnx files)
- 15 files, including 8 .onnx, 3 .json, 2 .md
- Last updated 2026-02-27
ONNX files
| File | Size | Download |
|---|---|---|
| fp32/onnx/model.onnx | — | Download |
| fp32/onnx/model_bnb4.onnx | — | Download |
| fp32/onnx/model_fp16.onnx | — | Download |
| fp32/onnx/model_int8.onnx | — | Download |
| fp32/onnx/model_q4.onnx | — | Download |
| fp32/onnx/model_q4f16.onnx | — | Download |
| fp32/onnx/model_quantized.onnx | — | Download |
| fp32/onnx/model_uint8.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
Speech Emotion Classification — ONNX (INT8)
ONNX INT8-quantized version of prithivMLmods/Speech-Emotion-Classification for on-device inference in macOS apps via ONNX Runtime C API.
Model Details
- Architecture: Wav2Vec2ForSequenceClassification (facebook/wav2vec2-base-960h fine-tuned)
- Format: ONNX INT8 quantized
- Size: ~91 MB (INT8), ~361 MB (FP32)
- Input: Raw audio waveform (16kHz, mono), shape
[1, num_samples] - Output: 8-class emotion logits
Emotion Labels
| ID | Label | Full |
|---|---|---|
| 0 | ANG | Anger |
| 1 | CAL | Calm |
| 2 | DIS | Disgust |
| 3 | FEA | Fear |
| 4 | HAP | Happy |
| 5 | NEU | Neutral |
| 6 | SAD | Sad |
| 7 | SUR | Surprised |
Usage
On-device real-time speech emotion classification. Inference via ONNX Runtime C API.
// Swift — load and run via OnnxRuntimeWrapper
let wrapper = OnnxRuntimeWrapper()
try wrapper.load(modelPath: "model_int8.onnx")
let logits = try wrapper.run(inputName: "input_values", inputData: audioBuffer, inputShape: [1, Int64(audioBuffer.count)])
let emotionIdx = logits.firstIndex(of: logits.max()!)!
Files
model_int8.onnx— INT8 quantized model (recommended for on-device use)model.onnx— FP32 full precision modelconfig.json— Model configuration with label mappings
Attribution
Original model by prithivMLmods. Converted to ONNX by onnx-community. INT8 quantization and packaging for macOS by @smkrv.
Model info
Created: 2026-02-27
Updated: 2026-02-27
View on Hugging Face