Downloads · 30 days
116
100% of all-time downloads
edgespeech-whisper-tiny-int8
VCoklat/edgespeech-whisper-tiny-int8
edgespeech-whisper-tiny-int8 is a machine learning model from VCoklat. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
Dynamic INT8 quantized weights for openai/whisper-tiny, optimized for low-latency, edge-native speech recognition directly in the browser via ONNX Runtime WebAssembly.
All-time downloads
116
Public
Repo size
297 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx189 MB · 99%
At a glance
- License
- mit
- Model type
- whisper
- Access
- Public
- Created
- Sep 8, 2026
- Updated
- Sep 17, 2026
- SHA
- 2f2e5383
Model card
From the Hugging Face model README
Whisper-tiny INT8 ONNX
Dynamic INT8 quantized weights for openai/whisper-tiny, optimized for low-latency, edge-native speech recognition directly in the browser via ONNX Runtime WebAssembly.
Model Summary
- Base Model:
openai/whisper-tiny - Quantization Method: Dynamic INT8 (
QuantType.QUInt8) - Total Repository Size: ~103.4 MB
- Active Runtime Footprint: ~56 MB (Only loads Encoder + KV-cache Decoder during streaming inference)
- Intended Use: Client-side ASR execution for
edgespeech-wasm
Files & Sizes
encoder_model_int8.onnx(~9.6 MB): Audio feature extractor & encoderdecoder_model_int8.onnx(~47.5 MB): Standard autoregressive text decoderdecoder_with_past_model_int8.onnx(~46.3 MB): Decoder optimized with KV-cache for low-latency streaming
- Type
- whisper
- License
- mit
- Languages
- en
- Created
- Sep 8, 2026
- Updated
- Sep 17, 2026