Uploading tflite to HF, dynamic quant version

.gitattributes

@@ -0,0 +1,9 @@
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text

EVALUATION.md

@@ -0,0 +1,61 @@
+# Evaluation Summary
+
+This folder contains a dynamic-range quantized TensorFlow Lite conversion of
+`KintsugiHealth/dam`. The evaluation below compares the converted TFLite model
+against official PyTorch DAM scores on DAIC-WOZ participant-only audio extracts.
+
+## Model Size
+
+| Model | Size | Relative |
+|---|---:|---:|
+| Legacy fp32 TFLite rebuild | 695.64 MiB | 1.00x |
+| Dynamic-range TFLite | 184.98 MiB | 0.266x |
+
+The dynamic-range model is approximately **73.4% smaller** / **3.76x smaller**.
+
+## Accuracy Comparison
+
+Evaluation target: official PyTorch DAM per-chunk scores aggregated with mean.
+
+| Task | Mean diff | MAE | Median AE | Max AE | Severity agreement |
+|---|---:|---:|---:|---:|---:|
+| Depression | +0.01310 | 0.01580 | 0.01421 | 0.04136 | 20/20 |
+| Anxiety | +0.01315 | 0.01580 | 0.01430 | 0.03887 | 20/20 |
+
+Per-chunk errors across the same 20 files:
+
+| Task | Per-chunk mean diff | Per-chunk MAE | Per-chunk max AE |
+|---|---:|---:|---:|
+| Depression | +0.01298 | 0.02206 | 0.08962 |
+| Anxiety | +0.01300 | 0.02137 | 0.09266 |
+
+## Threshold Agreement
+
+No depression or anxiety severity levels changed across the 20 DAIC-WOZ files
+tested.
+
+Thresholds used:
+
+- Depression: `[-0.6699, -0.2908]`
+- Anxiety: `[-0.7939, -0.2173, 0.1521]`
+
+## Mac Smoke Test
+
+On macOS, participant `346` produced:
+
+| Metric | Depression | Anxiety |
+|---|---:|---:|
+| Official chunk mean | -0.1387869 | 0.0714643 |
+| Dynamic TFLite chunk mean | -0.1305877 | 0.0790043 |
+| MAE per chunk | 0.0153862 | 0.0136833 |
+| Max AE per chunk | 0.0504357 | 0.0470306 |
+| Correlation | 0.999382 | 0.999388 |
+
+## Limitations
+
+- DAIC-WOZ raw audio is not redistributed here.
+- The evaluation uses participant-only audio derived from DAIC-WOZ transcripts.
+- This is not a clinical validation of the quantized model; it is a conversion
+  fidelity check against official DAM outputs.
+- The model is not intended for diagnosis or self-diagnosis without clinical
+  oversight.

LICENSE

@@ -0,0 +1,176 @@
+Apache License
+Version 2.0, January 2004
+http://www.apache.org/licenses/
+
+TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+1. Definitions.
+
+"License" shall mean the terms and conditions for use, reproduction,
+and distribution as defined by Sections 1 through 9 of this document.
+
+"Licensor" shall mean the copyright owner or entity authorized by
+the copyright owner that is granting the License.
+
+"Legal Entity" shall mean the union of the acting entity and all
+other entities that control, are controlled by, or are under common
+control with that entity. For the purposes of this definition,
+"control" means (i) the power, direct or indirect, to cause the
+direction or management of such entity, whether by contract or
+otherwise, or (ii) ownership of fifty percent (50%) or more of the
+outstanding shares, or (iii) beneficial ownership of such entity.
+
+"You" (or "Your") shall mean an individual or Legal Entity
+exercising permissions granted by this License.
+
+"Source" form shall mean the preferred form for making modifications,
+including but not limited to software source code, documentation
+source, and configuration files.
+
+"Object" form shall mean any form resulting from mechanical
+transformation or translation of a Source form, including but
+not limited to compiled object code, generated documentation,
+and conversions to other media types.
+
+"Work" shall mean the work of authorship, whether in Source or
+Object form, made available under the License, as indicated by a
+copyright notice that is included in or attached to the work
+(an example is provided in the Appendix below).
+
+"Derivative Works" shall mean any work, whether in Source or Object
+form, that is based on (or derived from) the Work and for which the
+editorial revisions, annotations, elaborations, or other modifications
+represent, as a whole, an original work of authorship. For the purposes
+of this License, Derivative Works shall not include works that remain
+separable from, or merely link (or bind by name) to the interfaces of,
+the Work and Derivative Works thereof.
+
+"Contribution" shall mean any work of authorship, including
+the original version of the Work and any modifications or additions
+to that Work or Derivative Works thereof, that is intentionally
+submitted to Licensor for inclusion in the Work by the copyright owner
+or by an individual or Legal Entity authorized to submit on behalf of
+the copyright owner. For the purposes of this definition, "submitted"
+means any form of electronic, verbal, or written communication sent
+to the Licensor or its representatives, including but not limited to
+communication on electronic mailing lists, source code control systems,
+and issue tracking systems that are managed by, or on behalf of, the
+Licensor for the purpose of discussing and improving the Work, but
+excluding communication that is conspicuously marked or otherwise
+designated in writing by the copyright owner as "Not a Contribution."
+
+"Contributor" shall mean Licensor and any individual or Legal Entity
+on behalf of whom a Contribution has been received by Licensor and
+subsequently incorporated within the Work.
+
+2. Grant of Copyright License. Subject to the terms and conditions of
+this License, each Contributor hereby grants to You a perpetual,
+worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+copyright license to reproduce, prepare Derivative Works of,
+publicly display, publicly perform, sublicense, and distribute the
+Work and such Derivative Works in Source or Object form.
+
+3. Grant of Patent License. Subject to the terms and conditions of
+this License, each Contributor hereby grants to You a perpetual,
+worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+(except as stated in this section) patent license to make, have made,
+use, offer to sell, sell, import, and otherwise transfer the Work,
+where such license applies only to those patent claims licensable
+by such Contributor that are necessarily infringed by their
+Contribution(s) alone or by combination of their Contribution(s)
+with the Work to which such Contribution(s) was submitted. If You
+institute patent litigation against any entity (including a
+cross-claim or counterclaim in a lawsuit) alleging that the Work
+or a Contribution incorporated within the Work constitutes direct
+or contributory patent infringement, then any patent licenses
+granted to You under this License for that Work shall terminate
+as of the date such litigation is filed.
+
+4. Redistribution. You may reproduce and distribute copies of the
+Work or Derivative Works thereof in any medium, with or without
+modifications, and in Source or Object form, provided that You
+meet the following conditions:
+
+(a) You must give any other recipients of the Work or
+Derivative Works a copy of this License; and
+
+(b) You must cause any modified files to carry prominent notices
+stating that You changed the files; and
+
+(c) You must retain, in the Source form of any Derivative Works
+that You distribute, all copyright, patent, trademark, and
+attribution notices from the Source form of the Work,
+excluding those notices that do not pertain to any part of
+the Derivative Works; and
+
+(d) If the Work includes a "NOTICE" text file as part of its
+distribution, then any Derivative Works that You distribute must
+include a readable copy of the attribution notices contained
+within such NOTICE file, excluding those notices that do not
+pertain to any part of the Derivative Works, in at least one
+of the following places: within a NOTICE text file distributed
+as part of the Derivative Works; within the Source form or
+documentation, if provided along with the Derivative Works; or,
+within a display generated by the Derivative Works, if and
+wherever such third-party notices normally appear. The contents
+of the NOTICE file are for informational purposes only and
+do not modify the License. You may add Your own attribution
+notices within Derivative Works that You distribute, alongside
+or as an addendum to the NOTICE text from the Work, provided
+that such additional attribution notices cannot be construed
+as modifying the License.
+
+You may add Your own copyright statement to Your modifications and
+may provide additional or different license terms and conditions
+for use, reproduction, or distribution of Your modifications, or
+for any such Derivative Works as a whole, provided Your use,
+reproduction, and distribution of the Work otherwise complies with
+the conditions stated in this License.
+
+5. Submission of Contributions. Unless You explicitly state otherwise,
+any Contribution intentionally submitted for inclusion in the Work
+by You to the Licensor shall be under the terms and conditions of
+this License, without any additional terms or conditions.
+Notwithstanding the above, nothing herein shall supersede or modify
+the terms of any separate license agreement you may have executed
+with Licensor regarding such Contributions.
+
+6. Trademarks. This License does not grant permission to use the trade
+names, trademarks, service marks, or product names of the Licensor,
+except as required for reasonable and customary use in describing the
+origin of the Work and reproducing the content of the NOTICE file.
+
+7. Disclaimer of Warranty. Unless required by applicable law or
+agreed to in writing, Licensor provides the Work (and each
+Contributor provides its Contributions) on an "AS IS" BASIS,
+WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+implied, including, without limitation, any warranties or conditions
+of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+PARTICULAR PURPOSE. You are solely responsible for determining the
+appropriateness of using or redistributing the Work and assume any
+risks associated with Your exercise of permissions under this License.
+
+8. Limitation of Liability. In no event and under no legal theory,
+whether in tort (including negligence), contract, or otherwise,
+unless required by applicable law (such as deliberate and grossly
+negligent acts) or agreed to in writing, shall any Contributor be
+liable to You for damages, including any direct, indirect, special,
+incidental, or consequential damages of any character arising as a
+result of this License or out of the use or inability to use the
+Work (including but not limited to damages for loss of goodwill,
+work stoppage, computer failure or malfunction, or any and all
+other commercial damages or losses), even if such Contributor
+has been advised of the possibility of such damages.
+
+9. Accepting Warranty or Additional Liability. While redistributing
+the Work or Derivative Works thereof, You may choose to offer,
+and charge a fee for, acceptance of support, warranty, indemnity,
+or other liability obligations and/or rights consistent with this
+License. However, in accepting such obligations, You may act only
+on Your own behalf and on Your sole responsibility, not on behalf
+of any other Contributor, and only if You agree to indemnify,
+defend, and hold each Contributor harmless for any liability
+incurred by, or claims asserted against, such Contributor by reason
+of your accepting any such warranty or additional liability.
+
+END OF TERMS AND CONDITIONS

NOTICE

@@ -0,0 +1,16 @@
+This repository contains a dynamic-range quantized TensorFlow Lite conversion
+of the Kintsugi Health Depression-Anxiety Model (DAM).
+
+Original model:
+- Hugging Face: https://huggingface.co/KintsugiHealth/dam
+- Source model ID: KintsugiHealth/dam
+- Base model: openai/whisper-small.en
+- Original model card license metadata: apache-2.0
+
+This derivative repository publishes only converted TensorFlow Lite weights and
+conversion/evaluation documentation. It does not include the original PyTorch
+checkpoint or any DAIC-WOZ audio.
+
+Clinical/safety note: DAM is intended for research, screening, clinical decision
+support, and monitoring workflows. It is not intended for diagnosis or
+self-diagnosis without clinical oversight.

ORIGINAL_MODEL_CARD_REFERENCE.md

@@ -0,0 +1,31 @@
+# Original Model Card Reference
+
+The original DAM model card is available at:
+
+https://huggingface.co/KintsugiHealth/dam
+
+The local source checkout used during conversion contained the original model
+card in `dam/README.md` with the following metadata:
+
+```yaml
+license: apache-2.0
+language:
+- en
+base_model:
+- openai/whisper-small.en
+pipeline_tag: audio-classification
+```
+
+This quantized-weight repository is a derivative conversion and does not replace
+the original model card. Users should read the original model card for clinical
+context, intended use, limitations, data description, tuning guidance, and
+references.
+
+Original model summary from `KintsugiHealth/dam`:
+
+- DAM is a speech-based model designed to screen for signs of depression and
+  anxiety using voice biomarkers.
+- It operates on acoustic properties of speech rather than transcribed content.
+- It outputs raw depression and anxiety scores that can be thresholded into
+  severity levels.
+- It is not intended for diagnosis or self-diagnosis without clinical oversight.

PUBLISH_TO_HUGGINGFACE.md

@@ -0,0 +1,184 @@
+# Step-by-Step Publishing Guide
+
+This guide publishes the contents of `tflite-dynamic-range-quant/` as a Hugging
+Face model repository containing only the converted dynamic-range TFLite weights
+and evaluation documentation.
+
+## 1. Review the Folder
+
+Expected files:
+
+```text
+tflite-dynamic-range-quant/
+├── .gitattributes
+├── LICENSE
+├── NOTICE
+├── README.md
+├── EVALUATION.md
+├── evaluation_results.json
+├── dam_features_scores_dynamic_range.metadata.json
+└── dam_features_scores_dynamic_range.tflite
+```
+
+Confirm the model file checksum if desired:
+
+```bash
+python - <<'PY'
+from pathlib import Path
+import hashlib
+p = Path('tflite-dynamic-range-quant/dam_features_scores_dynamic_range.tflite')
+print(p.stat().st_size / 1024 / 1024, 'MiB')
+print(hashlib.sha256(p.read_bytes()).hexdigest())
+PY
+```
+
+Expected SHA256:
+
+```text
+c9540444d577612a036ce8c4f24ce08d734b1b4ef90846b89600a73401dedab8
+```
+
+## 2. Install Hugging Face Tools
+
+```bash
+python -m pip install -U huggingface_hub hf_transfer
+```
+
+Optional, for faster uploads:
+
+```bash
+export HF_HUB_ENABLE_HF_TRANSFER=1
+```
+
+## 3. Log In
+
+```bash
+huggingface-cli login
+```
+
+Paste a write token from:
+
+```text
+https://huggingface.co/settings/tokens
+```
+
+## 4. Choose a Repository ID
+
+Examples:
+
+```text
+YOUR_USERNAME/dam-tflite-dynamic-range
+YOUR_ORG/dam-tflite-dynamic-range
+```
+
+Set it in your shell:
+
+```bash
+export HF_REPO_ID="YOUR_USERNAME/dam-tflite-dynamic-range"
+```
+
+## 5. Create the Hugging Face Repo
+
+```bash
+huggingface-cli repo create "$HF_REPO_ID" --type model
+```
+
+If you want it private first:
+
+```bash
+huggingface-cli repo create "$HF_REPO_ID" --type model --private
+```
+
+## 6. Upload the Folder
+
+From the project root:
+
+```bash
+huggingface-cli upload "$HF_REPO_ID" tflite-dynamic-range-quant/ . --repo-type model
+```
+
+Alternative Python upload:
+
+```bash
+python - <<'PY'
+import os
+from huggingface_hub import HfApi
+
+repo_id = os.environ['HF_REPO_ID']
+api = HfApi()
+api.upload_folder(
+    repo_id=repo_id,
+    repo_type='model',
+    folder_path='tflite-dynamic-range-quant',
+    path_in_repo='.',
+)
+print(f'Uploaded to https://huggingface.co/{repo_id}')
+PY
+```
+
+## 7. Edit Runtime Download Snippet
+
+After publishing, update `README.md` in the Hugging Face UI or locally by
+replacing:
+
+```text
+YOUR_USERNAME_OR_ORG/YOUR_REPO_NAME
+```
+
+with your actual repo ID.
+
+Then upload the README again if edited locally:
+
+```bash
+huggingface-cli upload "$HF_REPO_ID" tflite-dynamic-range-quant/README.md README.md --repo-type model
+```
+
+## 8. Test Download
+
+```bash
+python - <<'PY'
+import os
+from huggingface_hub import hf_hub_download
+
+repo_id = os.environ['HF_REPO_ID']
+path = hf_hub_download(repo_id=repo_id, filename='dam_features_scores_dynamic_range.tflite')
+print(path)
+PY
+```
+
+## 9. Runtime Download Example
+
+Use this in your app/backend tooling:
+
+```python
+from huggingface_hub import hf_hub_download
+
+model_path = hf_hub_download(
+    repo_id="YOUR_USERNAME/dam-tflite-dynamic-range",
+    filename="dam_features_scores_dynamic_range.tflite",
+)
+```
+
+For mobile apps, usually download once, verify checksum, and cache the file in
+app-private storage.
+
+## 10. Suggested Release Notes
+
+```text
+Initial release: dynamic-range quantized TFLite conversion of KintsugiHealth/dam.
+
+- Publishes converted TFLite weights only.
+- Input/output remain float32: [1, 80, 3000] -> [2].
+- Size reduced from 695.64 MiB to 184.98 MiB (~73.4% smaller).
+- DAIC-WOZ participant-only conversion-fidelity check: 20/20 depression and
+  20/20 anxiety severity-level agreement vs official PyTorch chunk-mean scores.
+```
+
+## 11. Important Compliance Notes
+
+- Keep attribution to `KintsugiHealth/dam` in the README and NOTICE.
+- Do not upload DAIC-WOZ raw audio or derived private data.
+- Keep clinical limitation language visible in the model card.
+- If publishing under an organization, verify that your intended use and
+  redistribution comply with the original Apache-2.0 license and any applicable
+  institutional/data-use requirements.

README.md

@@ -0,0 +1,177 @@
+---
+license: apache-2.0
+language:
+- en
+base_model:
+- KintsugiHealth/dam
+- openai/whisper-small.en
+pipeline_tag: audio-classification
+tags:
+- tflite
+- dynamic-range-quantization
+- audio-classification
+- mental-health
+- depression
+- anxiety
+- whisper
+library_name: tensorflow-lite
+---
+
+# DAM TFLite Dynamic-Range Quantized Weights
+
+This repository publishes a **dynamic-range quantized TensorFlow Lite** version
+of the Kintsugi Health Depression-Anxiety Model (DAM):
+[`KintsugiHealth/dam`](https://huggingface.co/KintsugiHealth/dam).
+
+Only the converted TFLite weights and conversion/evaluation metadata are
+published here. The original PyTorch checkpoint, original training data, and
+DAIC-WOZ audio are not included.
+
+## Relationship to the Original Model
+
+This is a derivative conversion of `KintsugiHealth/dam` for smaller on-device
+runtime deployment. For the original model card, intended use, limitations,
+clinical context, and references, see:
+
+- Original model: https://huggingface.co/KintsugiHealth/dam
+- Original license metadata: Apache-2.0
+- Base model: `openai/whisper-small.en`
+
+This model card intentionally separates the converted-weight details from the
+original DAM model card. The original clinical and safety limitations still
+apply.
+
+## Files
+
+| File | Description |
+|---|---|
+| `dam_features_scores_dynamic_range.tflite` | Dynamic-range quantized TFLite model |
+| `dam_features_scores_dynamic_range.metadata.json` | Input/output metadata and thresholds |
+| `evaluation_results.json` | Machine-readable size/accuracy summary |
+| `EVALUATION.md` | Human-readable evaluation summary |
+| `NOTICE` | Derivative-work and original-model attribution |
+| `LICENSE` | Apache License 2.0 |
+
+## Input / Output
+
+The model expects **precomputed DAM/Whisper log-mel features**, not raw audio.
+
+Input:
+
+```text
+dtype: float32
+shape: [1, 80, 3000]
+```
+
+Output:
+
+```text
+dtype: float32
+shape: [2]
+order: [depression_score, anxiety_score]
+```
+
+The app/runtime should perform the same preprocessing as DAM's `featex.py`:
+
+1. Load mono audio and resample to 16 kHz.
+2. Remove DC offset and normalize amplitude to `[-1, 1]`.
+3. Pad/split audio into 30-second chunks.
+4. Run Whisper log-mel feature extraction.
+5. Apply DAM log-mel energy rescaling.
+6. Run this TFLite model per chunk and aggregate scores as needed.
+
+## Quantization Type
+
+This is **dynamic-range quantization**:
+
+- input remains `float32`
+- output remains `float32`
+- weights are quantized/compressed internally by TensorFlow Lite
+
+No preprocessing or postprocessing dtype changes are required relative to the
+fp32 TFLite model.
+
+## Size and Accuracy
+
+| Model | Size | Relative |
+|---|---:|---:|
+| Legacy fp32 TFLite rebuild | 695.64 MiB | 1.00x |
+| Dynamic-range TFLite | 184.98 MiB | 0.266x |
+
+The dynamic-range model is approximately **73.4% smaller** / **3.76x smaller**.
+
+Evaluation on 20 DAIC-WOZ participant-only audio files showed:
+
+| Task | MAE vs official PyTorch chunk mean | Max AE | Severity agreement |
+|---|---:|---:|---:|
+| Depression | 0.01580 | 0.04136 | 20/20 |
+| Anxiety | 0.01580 | 0.03887 | 20/20 |
+
+See `EVALUATION.md` and `evaluation_results.json` for details.
+
+## Runtime Download Example
+
+```python
+from huggingface_hub import hf_hub_download
+
+model_path = hf_hub_download(
+    repo_id="pat229988/dam-tflite-dynamic-range",
+    filename="dam_features_scores_dynamic_range.tflite",
+)
+print(model_path)
+```
+
+## Loading with TensorFlow Lite / LiteRT
+
+```python
+import numpy as np
+
+try:
+    from ai_edge_litert.interpreter import Interpreter
+except Exception:
+    import tensorflow as tf
+    Interpreter = tf.lite.Interpreter
+
+interpreter = Interpreter(model_path="dam_features_scores_dynamic_range.tflite")
+interpreter.allocate_tensors()
+
+input_details = interpreter.get_input_details()[0]
+output_details = interpreter.get_output_details()[0]
+
+# features shape: [1, 80, 3000], dtype float32
+features = np.zeros((1, 80, 3000), dtype=np.float32)
+
+interpreter.set_tensor(input_details["index"], features)
+interpreter.invoke()
+scores = interpreter.get_tensor(output_details["index"]).reshape(-1)
+
+depression_score, anxiety_score = scores.tolist()
+```
+
+## Thresholds
+
+The metadata file includes the original DAM thresholds:
+
+```json
+{
+  "depression": [-0.6699, -0.2908],
+  "anxiety": [-0.7939, -0.2173, 0.1521]
+}
+```
+
+## Safety / Clinical Limitations
+
+- This model is not intended for diagnosis or self-diagnosis without clinical
+  oversight.
+- Performance may degrade with noisy audio, multiple speakers, non-English
+  speech, or recordings outside intended conditions.
+- This repository provides a conversion-fidelity evaluation, not an independent
+  clinical validation of the quantized model.
+
+## Attribution
+
+Original DAM model by Kintsugi Health:
+
+- https://huggingface.co/KintsugiHealth/dam
+- Source model ID: `KintsugiHealth/dam`
+- Original license metadata: Apache-2.0

dam_features_scores_dynamic_range.metadata.json

@@ -0,0 +1,52 @@
+{
+  "source_model": "KintsugiHealth/dam",
+  "model_dir": "dam",
+  "input": {
+    "name": "whisper_logmel_features",
+    "dtype": "float32",
+    "shape": [
+      1,
+      80,
+      3000
+    ],
+    "description": "Preprocessed DAM/Whisper log-mel features, not raw audio."
+  },
+  "output": {
+    "dtype": "float32",
+    "shape": [
+      2
+    ],
+    "labels": [
+      "depression_score",
+      "anxiety_score"
+    ]
+  },
+  "preprocessing": {
+    "sample_rate_hz": 16000,
+    "chunk_seconds": 30,
+    "n_mels": 80,
+    "n_frames": 3000,
+    "notes": [
+      "Load mono audio and resample to 16 kHz.",
+      "Remove DC offset and normalize amplitude to [-1, 1].",
+      "Pad/split audio into 30-second chunks.",
+      "Run Whisper log-mel feature extraction as in DAM featex.py.",
+      "Apply DAM logmel_energies rescale before inference."
+    ]
+  },
+  "thresholds": {
+    "depression": [
+      -0.6699,
+      -0.2908
+    ],
+    "anxiety": [
+      -0.7939,
+      -0.2173,
+      0.1521
+    ]
+  },
+  "raw_score_order": [
+    "depression",
+    "anxiety"
+  ]
+}

dam_features_scores_dynamic_range.tflite

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9540444d577612a036ce8c4f24ce08d734b1b4ef90846b89600a73401dedab8
+size 193966344

evaluation_results.json

@@ -0,0 +1,76 @@
+{
+  "model": {
+    "name": "dam_features_scores_dynamic_range.tflite",
+    "source_model": "KintsugiHealth/dam",
+    "conversion": "TensorFlow Lite dynamic-range quantization",
+    "input": {
+      "dtype": "float32",
+      "shape": [1, 80, 3000]
+    },
+    "output": {
+      "dtype": "float32",
+      "shape": [2],
+      "order": ["depression", "anxiety"]
+    },
+    "file_size_mib": 184.98072052001953,
+    "sha256": "c9540444d577612a036ce8c4f24ce08d734b1b4ef90846b89600a73401dedab8"
+  },
+  "baseline": {
+    "name": "legacy fp32 TFLite rebuild",
+    "file_size_mib": 695.6440963745117
+  },
+  "size_comparison": {
+    "absolute_reduction_mib": 510.6633758544922,
+    "relative_size_ratio": 0.2659128733846568,
+    "relative_reduction_percent": 73.40871266153432,
+    "smaller_by_factor": 3.760631267572199
+  },
+  "evaluation": {
+    "dataset": "DAIC-WOZ participant-only audio extracts",
+    "num_audio_files": 20,
+    "comparison_target": "official PyTorch DAM per-chunk scores aggregated by mean",
+    "aggregation": "chunk_mean",
+    "depression": {
+      "mean_diff_dynamic_minus_official": 0.013095549532314881,
+      "mean_absolute_error": 0.01580149956564844,
+      "median_absolute_error": 0.014209017778436417,
+      "max_absolute_error": 0.0413626036606729,
+      "severity_level_agreement": "20/20",
+      "per_chunk_mean_diff": 0.012983481563285841,
+      "per_chunk_mean_absolute_error": 0.022058436869572894,
+      "per_chunk_max_absolute_error": 0.089621901512146
+    },
+    "anxiety": {
+      "mean_diff_dynamic_minus_official": 0.013152226906022909,
+      "mean_absolute_error": 0.015800999800324254,
+      "median_absolute_error": 0.014297692570835352,
+      "max_absolute_error": 0.0388676428119652,
+      "severity_level_agreement": "20/20",
+      "per_chunk_mean_diff": 0.012999067678340252,
+      "per_chunk_mean_absolute_error": 0.021374379997907936,
+      "per_chunk_max_absolute_error": 0.09266304969787598
+    }
+  },
+  "mac_smoke_test_346": {
+    "file": "results/mac-dynamic-test-chunkmean.jsonl",
+    "dynamic_file_size_mib": 184.98072052001953,
+    "official_chunk_mean": {
+      "depression": -0.13878686849027871,
+      "anxiety": 0.07146425396203995
+    },
+    "dynamic_chunk_mean": {
+      "depression": -0.13058771580457687,
+      "anxiety": 0.07900430142879486
+    },
+    "depression": {
+      "mean_absolute_error": 0.015386152900755406,
+      "max_absolute_error": 0.05043572187423706,
+      "correlation": 0.9993821695348476
+    },
+    "anxiety": {
+      "mean_absolute_error": 0.013683260977268219,
+      "max_absolute_error": 0.047030627727508545,
+      "correlation": 0.999388358572843
+    }
+  }
+}