Sync model repo (text/metadata)

README.md

@@ -48,6 +48,10 @@ This version is intended to demonstrate efficient inference on Arm-based platfor
 |---|---|
 | `whisper_small_vivo_executorch_optimized.pte` | Arm-optimized model for deployment |
 | `whisper_preprocessor.pte` | ExecuTorch module that computes the log-mel spectrogram from raw audio; loaded by `example.py` when present, with a Python-side fallback otherwise |
+| `tokenizer.json` | Fast Whisper tokenizer vocabulary and tokenisation rules |
+| `tokenizer_config.json` | Whisper tokenizer configuration |
+| `special_tokens_map.json` | Whisper special-token definitions |
+| `pte_original/` | Original baseline model and tokenizer artefacts; not used by the optimised example |
 | `example.py` | Minimal inference example |
 | `pyproject.toml` | Pinned runtime dependencies for `example.py`, resolved with uv |
 | `uv.lock` | Locked dependency resolution for `pyproject.toml` |

example.py

@@ -6,8 +6,10 @@ all Linear layers plus a manual weight-only INT8 pass on `decoder.embed_tokens`,
 and uses separate 'encoder' and 'text_decoder' ExecuTorch methods with a
 static KV cache.
 
-This example resolves the tokenizer and preprocessor artifacts from the same
-directory as the model, matching the benchmark flow used by the Whisper runner.
+This example resolves the model, tokenizer, and preprocessor artifacts from the
+repository root.
+Original baseline artifacts are retained in the pte_original directory and are
+not used by this optimized example.
 
 Requirements:
     pip install executorch torch transformers soundfile numpy
@@ -26,7 +28,6 @@ from transformers import AutoTokenizer
 # -- Configuration -------------------------------------------------------------
 AUDIO_PATH = "sample_input.flac"
 PREPROCESSOR_FILENAME = "whisper_preprocessor.pte"
-DEFAULT_LOCAL_MODEL_DIR = "pte_optimized"
 MODEL_FILENAME = "whisper_small_vivo_executorch_optimized.pte"
 
 DECODER_START_TOKEN_ID = 50258
@@ -60,7 +61,7 @@ def parse_args() -> argparse.Namespace:
         default=None,
         help=(
             "Directory containing the ExecuTorch model, tokenizer files, and optionally "
-            "whisper_preprocessor.pte. Defaults to the local huggingface bundle."
+            "whisper_preprocessor.pte. Defaults to the directory containing example.py."
         ),
     )
     parser.add_argument(
@@ -75,7 +76,7 @@ def resolve_model_dir(script_dir: Path, requested_dir: str | None) -> Path:
     candidates: list[Path] = []
     if requested_dir:
         candidates.append(Path(requested_dir))
-    candidates.append(script_dir / DEFAULT_LOCAL_MODEL_DIR)
+    candidates.append(script_dir)
 
     for candidate in candidates:
         bundle_dir = candidate.resolve()