dkhokhlov/whisper-tiny-hqq-4bit
Upload model.safetensors with huggingface_hub
Upload README.md with huggingface_hub
Upload README.md with huggingface_hub
v1.9.5: gate-confirmed fp16+fp32 ONNX card (two-variant, corrected base+small gate results)
Delete decoder_model_merged-fp16.onnx with huggingface_hub
Delete encoder_model-fp16.onnx with huggingface_hub
Upload decoder_model_merged.onnx with huggingface_hub
Upload encoder_model.onnx with huggingface_hub
Upload decoder_model_merged-fp32.onnx with huggingface_hub
Upload encoder_model-fp32.onnx with huggingface_hub
Upload decoder_model_merged-fp16.onnx with huggingface_hub
Upload encoder_model-fp16.onnx with huggingface_hub
Upload README.md with huggingface_hub
Delete decoder_with_past_model.onnx with huggingface_hub
Delete decoder_model.onnx with huggingface_hub
Upload README.md with huggingface_hub
Upload README.md with huggingface_hub
Upload folder using huggingface_hub
v1.8.1: slim card + corrected fp16-compute resident RAM headline (vs fp16 original)
card: headline deployment RAM (fp16); drop mu-bench; reflinks; deployment loader wording
Upload README.md with huggingface_hub
Upload README.md with huggingface_hub
Upload model.safetensors with huggingface_hub
v1.5.1: add bold cross-reference table caption
v1.5.0: cross-reference table, Delta % columns, reflinks, base_model provenance
Upload README.md with huggingface_hub
Upload folder using huggingface_hub
Upload folder using huggingface_hub
Upload README.md with huggingface_hub
Upload folder using huggingface_hub
initial commit