software-mansion/react-native-executorch-whisper-small

Add XNNPACK int8 (8da4w): WER +0.1 to +2.7 vs fp32 on en/de/es/pl/fr/zh

Apply the model card standard

Apply the model card standard

Stop restating quantized, and drop the unused default

Correct the published metadata

Add Vulkan variants (fp16, int8)

perf(coreml): run decode on the CPU, not the Neural Engine

perf(coreml): run decode on the CPU, not the Neural Engine

Add int8 MLX variant; remove bf16 (OOM-killed on device)

Update .pte files for v0.10.0

Replace .pte files with reexported versions including dynamic dims companion methods

Replace .pte files with reexported versions including dynamic dims companion methods

Update README.md

Add MLX model

remove old fp32

fix(v0.9.0): add missing coreml/config.json

Add stub root config.json for HF download counter

Add CoreML model

Add spec-compliant config.json files

Add spec-compliant config.json files

Remove old-layout metadata orphaned by MODEL_SPEC.md restructure

Restructure to MODEL_SPEC.md convention

Update README.md

Improve exported model & bundle methods

v0.6.0

Upload tokenizer.json

Upload 2 files

Create config.json

Update README.md

initial commit