schema_version: 1.0.0
report_type: speech-asr
task_type: automatic-speech-recognition
title: Whisper Small INT8
description: >-
  A compact INT8-quantized speech recognition model for transcribing 16 kHz audio, using an
  encoder-decoder Transformer that converts log-mel spectrograms into text tokens. It combines dynamic
  INT8 linear layers with selective FP32 components to reduce size and improve inference efficiency
  while preserving transcription quality.
id: Arm/whisper-small-int8-xnnpack-executorch
filename: whisper_small_vivo_executorch_optimized.pte
base_model_id: openai/whisper-small
vendor: OpenAI
base_model_url: https://huggingface.co/openai/whisper-small
profile: Arm-Optimized
weight_dtype: int8
quantization:
  method: PTQ-dynamic
  weight_bits: 8
  activation_bits: 8
  symmetric: true
  mode: dynamic
  weight_granularity: per-channel
  variant: 8da8w + embed_tokens weight-only int8
  fp32_layers:
  - embed_positions
model_size_mb: 395.046
parameter_count: 241734912
format: pte