devendradhakad/autodroid-litert-community-Kokoro-G2P-en-US

Kokoro G2P (en-US) — LiteRT (preview)

⚠️ Labeled preview — fixed-length [1, 96], FP32, CPU. Shared to complete the on-device Kokoro front-end per the LiteRT community direction ③.

A LiteRT (.tflite) conversion of DeepPhonemizer en_us_cmudict_forward (a small non-autoregressive forward Transformer), used as the neural grapheme-to-phoneme (G2P) front-end for on-device Kokoro-82M TTS. It gives Kokoro a phonemizer fallback so arbitrary free text — names, brands, numbers — synthesizes with zero dropped words when the dictionary phonemizer misses.

Files

File	Precision	Size
dp_g2p_litert.tflite	fp32	~51 MB

Specs

Task	Grapheme-to-phoneme (English)
Source	DeepPhonemizer en_us_cmudict_forward
Input	1 × 96 character IDs (fixed length 96, in-graph padding mask)
Output	per-position phoneme logits → ARPABET / IPA
Runtime	CPU (LiteRT CompiledModel API)
Verified	Pixel 8a — 12/12 vs the reference G2P, no dropped words

How it was converted / why CPU

• Stock official converter (litert_torch), static-shape graph: the dynamic-length export hits the same symbolic-sequence-length wall as the TTS model (Shapes must be 1D sequences of concrete values…) — the dynamic-shape converter class. Worked around with a static [1, 96] graph + an in-graph padding mask; converts cleanly and is numerically correct.
• CPU-only: the attention's fused-QKV 5-D layout + the mask's EQUAL / SELECT_V2 keep it off the GPU delegate; decomposing the attention to ≤ 4-D would clear that.

Training data

DeepPhonemizer en_us_cmudict_forward is trained on the CMU Pronouncing Dictionary (CMUdict) — ~126k common English words paired with ARPABET pronunciations (a public pronunciation lexicon). It learns the grapheme→phoneme spelling-to-sound mapping only. This LiteRT artifact is a format conversion of the released checkpoint and introduces no additional training data.

PII

No personally identifiable information. CMUdict is a public dictionary of common English word pronunciations (no personal data); none is added during conversion.

Roadmap

• Variable-length + quantized + (ideally) GPU is gated on the dynamic-shape converter work and a ≤ 4-D attention re-author.

Status

Labeled preview — part of an on-device free-text Kokoro-82M LiteRT pipeline; the official litert-samples text_to_speech sample is in review at google-ai-edge/litert-samples #159.

Performance

Measured on an Apple M4 Max, CPU/XNNPACK at 8 threads, ai-edge-litert 2.1.6 — median of 15 warm runs per graph, with zero-filled inputs of each graph's declared static shape. Run-to-run spread stayed within 5%.

Graph	Warm median	First call
dp_g2p_litert.tflite	4.4 ms	9.6 ms

One call converts a padded 96-character window into per-position phoneme logits, so grapheme-to-phoneme conversion is a rounding error next to the acoustic model and vocoder it feeds.

Android (Pixel 8a)

Android figures use the standard TFLite benchmark_model on a Pixel 8a (Tensor G3, Android 16) — 5 warm-up runs then 20 timed runs, CPU at 4 threads.

Graph	GPU (OpenCL)	CPU (XNNPACK, 4 threads)
dp_g2p_litert.tflite	did not run	43 ms

1 of these graphs do not load on the OpenCL delegate at all, so the CPU column is the only Android number for them. Nothing here is faster on the GPU; run this pipeline on the CPU on Android.

License

MIT. Full attribution to DeepPhonemizer and the en_us_cmudict_forward checkpoint.