1.67 GB

Ctrl+K

2 contributors

History: 4 commits

alexwengg

feat(voice-cloning): per-language mimi_encoderv3 for german (#793)

6a1407e verified about 1 hour ago

cond_prefill.mlmodelc
Add v2.1 english (optimized: fused decoder ANE + cond prefill + fp16 flowlm; same weights as v2) (#3) 2 months ago
cond_prefill.mlpackage
Add v2.1 english (optimized: fused decoder ANE + cond prefill + fp16 flowlm; same weights as v2) (#3) 2 months ago
cond_prefill_ane.mlmodelc
feat(v2.1): ANE-eligible flowlm_step_ane + cond_prefill_ane for all 9 remaining language packs (german/italian/portuguese/spanish 6L + french/german/italian/portuguese/spanish 24L). Rank-4 split-KV, scatter-free, explicit output names, no NaN-BOS protocol (mobius Trials 19/20). flowlm 100% ANE on every pack incl. 24L (1830 ops). Loaded by FluidAudio PocketTtsModelPlacement.ane. 2 months ago
cond_prefill_ane.mlpackage
feat(v2.1): ANE-eligible flowlm_step_ane + cond_prefill_ane for all 9 remaining language packs (german/italian/portuguese/spanish 6L + french/german/italian/portuguese/spanish 24L). Rank-4 split-KV, scatter-free, explicit output names, no NaN-BOS protocol (mobius Trials 19/20). flowlm 100% ANE on every pack incl. 24L (1830 ops). Loaded by FluidAudio PocketTtsModelPlacement.ane. 2 months ago
constants
Add v2.1 english (optimized: fused decoder ANE + cond prefill + fp16 flowlm; same weights as v2) (#3) 2 months ago
constants_bin
Add v2.1 english (optimized: fused decoder ANE + cond prefill + fp16 flowlm; same weights as v2) (#3) 2 months ago
flow_decoder_fused.mlmodelc
Add v2.1 english (optimized: fused decoder ANE + cond prefill + fp16 flowlm; same weights as v2) (#3) 2 months ago
flow_decoder_fused.mlpackage
Add v2.1 english (optimized: fused decoder ANE + cond prefill + fp16 flowlm; same weights as v2) (#3) 2 months ago
flowlm_step.mlmodelc
Add v2.1 english (optimized: fused decoder ANE + cond prefill + fp16 flowlm; same weights as v2) (#3) 2 months ago
flowlm_step.mlpackage
Add v2.1 english (optimized: fused decoder ANE + cond prefill + fp16 flowlm; same weights as v2) (#3) 2 months ago
flowlm_step_ane.mlmodelc
feat(v2.1): ANE-eligible flowlm_step_ane + cond_prefill_ane for all 9 remaining language packs (german/italian/portuguese/spanish 6L + french/german/italian/portuguese/spanish 24L). Rank-4 split-KV, scatter-free, explicit output names, no NaN-BOS protocol (mobius Trials 19/20). flowlm 100% ANE on every pack incl. 24L (1830 ops). Loaded by FluidAudio PocketTtsModelPlacement.ane. 2 months ago
flowlm_step_ane.mlpackage
feat(v2.1): ANE-eligible flowlm_step_ane + cond_prefill_ane for all 9 remaining language packs (german/italian/portuguese/spanish 6L + french/german/italian/portuguese/spanish 24L). Rank-4 split-KV, scatter-free, explicit output names, no NaN-BOS protocol (mobius Trials 19/20). flowlm 100% ANE on every pack incl. 24L (1830 ops). Loaded by FluidAudio PocketTtsModelPlacement.ane. 2 months ago
flowlm_stepv2.mlmodelc
Add v2.1 english (optimized: fused decoder ANE + cond prefill + fp16 flowlm; same weights as v2) (#3) 2 months ago
flowlm_stepv2.mlpackage
Add v2.1 english (optimized: fused decoder ANE + cond prefill + fp16 flowlm; same weights as v2) (#3) 2 months ago
mimi_decoder.mlmodelc
Add v2.1 english (optimized: fused decoder ANE + cond prefill + fp16 flowlm; same weights as v2) (#3) 2 months ago
mimi_decoder.mlpackage
Add v2.1 english (optimized: fused decoder ANE + cond prefill + fp16 flowlm; same weights as v2) (#3) 2 months ago
mimi_encoderv3.mlmodelc
feat(voice-cloning): per-language mimi_encoderv3 for german (#793) about 1 hour ago
mimi_encoderv3.mlpackage
feat(voice-cloning): per-language mimi_encoderv3 for german (#793) about 1 hour ago
manifest.json

739 Bytes
Add v2.1 english (optimized: fused decoder ANE + cond prefill + fp16 flowlm; same weights as v2) (#3) 2 months ago