Update model card: current presets, venue, and usage snippet

Replaces the five-preset table with the two presets that ship (default, torgo) and fixes the usage snippet, which called load_preset("star_v5") for a preset that no longer exists. Adds the GPU memory the training recipe needs and the SLT 2026 venue; drops internal run filenames.

README.md

@@ -14,14 +14,14 @@ tags:
 
 # ChiReSSD
 
-Speaker-preserving reconstruction of pediatric disordered speech.
+Speaker-preserving reconstruction of disordered speech.
 
-Given a target transcript and a short reference recording from a child with a speech sound
-disorder (SSD), ChiReSSD synthesizes the target utterance with canonical pronunciation while
-keeping the child's voice and prosody. Pronunciation enters through the text pathway; identity
-and prosody come from the style pathway. That separation is the point: ordinary style-preserving
-TTS treats disordered articulation as part of the speaker's style and so reproduces the
-mispronunciation it was meant to correct.
+Given a target transcript and a short reference recording of a speaker, ChiReSSD synthesizes
+that transcript with canonical pronunciation while keeping the speaker's voice and prosody.
+Pronunciation enters through the text pathway; identity and prosody come from the style
+pathway. That separation is the point: ordinary style-preserving TTS treats disordered
+articulation as part of the speaker's style and so reproduces the mispronunciation it was
+meant to correct.
 
 - Code: <https://github.com/Lab-MSP/ChiReSSD>
 - Paper: *Generative Reconstruction of Pediatric Disordered Speech for Automated Clinical
@@ -29,27 +29,28 @@ mispronunciation it was meant to correct.
 
 ## Model description
 
-StyleTTS2 fine-tuned on child disordered speech. Two 128-dimensional style vectors are extracted
-from the reference recording — acoustic (timbre) and prosodic — and interpolated with a style
-sampled from the adapted diffusion prior. `alpha` weights the acoustic side and `beta` the
-prosodic; 1.0 is fully diffusion-sampled, 0.0 fully reference-driven.
+StyleTTS2 fine-tuned on child disordered speech. Two 128-dimensional style vectors are
+extracted from the reference recording — acoustic (timbre) and prosodic — and interpolated
+with a style sampled from the adapted diffusion prior. `alpha` weights the acoustic side and
+`beta` the prosodic; 1.0 is fully diffusion-sampled, 0.0 fully reference-driven.
 
-It works on unseen speakers from a reference as short as a few seconds. No per-child model is
-trained, and no paired typical/atypical recordings are required.
+It works on unseen speakers from a reference as short as a few seconds. No per-speaker model
+is trained, and no paired typical/atypical recordings are required.
 
 ## Base model and license chain
 
 Fine-tuned from the StyleTTS2 LibriTTS second-stage checkpoint by
-[yl4579](https://github.com/yl4579/StyleTTS2) (MIT). **That base checkpoint is not redistributed
-here** — obtain it from the upstream release. The frozen helper models (ASR text aligner, JDCNet
-pitch extractor, PL-BERT) likewise ship inside the upstream repository and are not redistributed.
+[yl4579](https://github.com/yl4579/StyleTTS2) (MIT). **That base checkpoint is not
+redistributed here** — obtain it from the upstream release. The frozen helper models (ASR text
+aligner, JDCNet pitch extractor, PL-BERT) likewise ship inside the upstream repository and are
+not redistributed.
 
 ChiReSSD's own modification to StyleTTS2 is two lines, published as patch files in the code
 repository rather than as a fork.
 
 ## Intended use
 
-Research on speech reconstruction and on automated clinical evaluation of pediatric speech sound
+Research on speech reconstruction and on automated clinical evaluation of speech sound
 disorders.
 
 ## Out of scope
@@ -64,9 +65,9 @@ disorders.
 
 Child speech from UltraSuite/CLP-derived recordings, obtained under their own data use
 agreements. **The corpus is not released here and is not redistributable**: it is identifiable
-child clinical speech. See `DATA.md` in the code repository for how to obtain comparable data;
-<https://huggingface.co/datasets/changelinglab/ultrasuite-benchmark> is a suitable starting point
-for fine-tuning your own model.
+child clinical speech. To fine-tune your own model,
+<https://huggingface.co/datasets/changelinglab/ultrasuite-benchmark> is a suitable starting
+point; see `DATA.md` in the code repository.
 
 ## Training configuration
 
@@ -84,41 +85,41 @@ for fine-tuning your own model.
 | Sample rate | 24 kHz |
 | LR schedule | OneCycleLR, `pct_start=0.1` (upstream: 0) |
 
-The heavy pitch weighting is deliberate: the pitch extractor was pretrained on adult voices, and
-children's F0 is both higher and more variable, so it needs the strongest adaptation of any
-component. Conversely, only four epochs — longer schedules start fitting the disordered
+The heavy pitch weighting is deliberate: the pitch extractor was pretrained on adult voices,
+and children's F0 is both higher and more variable, so it needs the strongest adaptation of
+any component. Conversely, only four epochs — longer schedules start fitting the disordered
 articulation itself.
 
+Trained on 2× 48 GB GPUs. At batch 4 and `max_len` 600 the recipe needs more than 48 GB, so a
+single smaller card requires lowering both.
+
 ## Inference
 
+Two presets ship with the code:
+
 | Preset | alpha | beta | steps | Purpose |
 |---|---|---|---|---|
-| `star_v5` | 0.8 | 0.5 | 10 | Released operating point |
-| `star_v5_alt` | 1.0 | 0.4 | 10 | Variant |
-| `star_oneshot_base` | 1.0 | 0.5 | 5 | One-shot baseline (no fine-tuning) |
-| `star_adult_tts` | 0.3 | 0.7 | 5 | Standard adult-TTS baseline |
-| `torgo_v5` | 1.0 | 0.5 | 15 | Adult dysarthric speech |
+| `default` | 0.8 | 0.5 | 10 | The released operating point |
+| `torgo` | 1.0 | 0.5 | 15 | Adult dysarthric speech |
 
 `alpha` is high on purpose. A low `alpha` leans on the reference acoustics, which is exactly
 where the disordered articulation lives.
 
-**Synthesis is stochastic.** The initial style latent is zeros rather than a Gaussian draw, but
-the ADPM2 sampler is ancestral and adds fresh noise at every step, so repeated calls differ in
-waveform and in duration. Pass a `seed` for reproducible output.
+**Synthesis is stochastic.** The initial style latent is zeros rather than a Gaussian draw,
+but the ADPM2 sampler is ancestral and adds fresh noise at every step, so repeated calls
+differ in waveform and in duration. Pass a `seed` for reproducible output.
 
 ## Evaluation
 
-See the paper. **This model repository does not reproduce the paper's reported numbers**, and the
-code repository does not either: the evaluation corpora are not redistributable, so the numbers
-cannot be independently recomputed from what is published here.
+See the paper.
 
 ## Ethical considerations
 
 This model is trained on identifiable clinical recordings of children and is designed to
-reproduce a child's vocal identity accurately. High speaker similarity is the method's goal and
-therefore also its misuse vector: the same property that makes feedback usable in a child's own
-voice makes the model a voice-cloning tool for a minor. Use it only with appropriate consent and
-ethical oversight.
+reproduce a speaker's vocal identity accurately. High speaker similarity is the method's goal
+and therefore also its misuse vector: the same property that makes feedback usable in a
+child's own voice makes the model a voice-cloning tool for a minor. Use it only with
+appropriate consent and ethical oversight.
 
 ## Usage
 
@@ -127,31 +128,34 @@ from chiressd.model import ChiReSSD
 from chiressd.config import load_preset
 
 model = ChiReSSD.from_pretrained()  # downloads this checkpoint
-style = model.compute_style("child_reference.wav")
+style = model.compute_style("speaker_reference.wav")
 wav = model.synthesize(
-    "butterfly butterfly butterfly", style, seed=1234, **load_preset("star_v5").as_kwargs()
+    "butterfly butterfly butterfly",
+    style,
+    seed=1234,
+    **load_preset("default").as_kwargs(),
 )
 ```
 
-Run `chiressd-setup` first: it clones and patches the upstream StyleTTS2 checkout that supplies
-the architecture and frozen helper models.
+Run `chiressd-setup` first: it clones and patches the upstream StyleTTS2 checkout that
+supplies the architecture and frozen helper models.
 
 ## Checkpoint provenance
 
-Derived from training checkpoint `epoch_2nd_00003.pth` of the v5 run by keeping `state['net']`
-only, removing the `module.` prefix that DataParallel added to ten of the thirteen submodules,
-and making every tensor detached, CPU-resident and contiguous. Precision is unchanged (float32;
-no fp16 cast, which would alter outputs).
+Derived from the fine-tuning run's final checkpoint by keeping `state['net']` only, removing
+the `module.` prefix that DataParallel added to ten of the thirteen submodules, and making
+every tensor detached, CPU-resident and contiguous. Precision is unchanged (float32; no fp16
+cast, which would alter outputs).
 
 - 2258 MB → 767 MB; the 1491 MB removed is optimizer state, which inference never reads
 - `sha256` of `model.pth`: `6c5faf5b4967b4d26cb4c58d4517dcc477729a579039316741bd88b9bd0f16e0`
 - Verified bit-exact against the training checkpoint it was stripped from: under a fixed seed,
-  the two produce an identical 256-d style vector and identical waveform samples, so the strip
-  provably changes no output
+  the two produce an identical 256-d style vector and identical waveform samples
 
 Full details in `manifest.json`.
 
 ## Citation
 
 Rosero, Yeo, Mortensen, Van't Slot, Hallac, and Busso. *Generative Reconstruction of Pediatric
-Disordered Speech for Automated Clinical Evaluation.*
+Disordered Speech for Automated Clinical Evaluation.* In Proceedings of the IEEE Spoken
+Language Technology Workshop 2026 (SLT '26), Palermo, Italy, 2026.