Upload pocket-tts/voices/gunny.bin.gz with huggingface_hub

Upload pocket-tts/voices/gary_thompson.bin.gz with huggingface_hub

Upload pocket-tts/voices/fabian.bin.gz with huggingface_hub

Upload pocket-tts/voices/dingus_the_wise.bin.gz with huggingface_hub

Upload pocket-tts/voices/biscuit.bin.gz with huggingface_hub

Upload pocket-tts/voices/ricky_rage.bin.gz with huggingface_hub

Upload pocket-tts/voices/miss_pearl.bin.gz with huggingface_hub

Upload pocket-tts/voices/voices_index.json with huggingface_hub

Upload pocket-tts/voices/gunny.json with huggingface_hub

Upload pocket-tts/voices/gunny.bin with huggingface_hub

Upload pocket-tts/voices/gary_thompson.json with huggingface_hub

Upload pocket-tts/voices/gary_thompson.bin with huggingface_hub

Upload pocket-tts/voices/fabian.json with huggingface_hub

Upload pocket-tts/voices/fabian.bin with huggingface_hub

Upload pocket-tts/voices/dingus_the_wise.json with huggingface_hub

Upload pocket-tts/voices/dingus_the_wise.bin with huggingface_hub

Upload pocket-tts/voices/biscuit.json with huggingface_hub

Upload pocket-tts/voices/biscuit.bin with huggingface_hub

Upload pocket-tts/voices/ricky_rage.bin with huggingface_hub

Add chip-specific model: models/gemma-4-E2B-it-tensor-g5.litertlm

Add chip-specific model: models/gemma-4-E2B-it-qualcomm-qcs8275.litertlm

Add chip-specific model: models/gemma-4-E2B-it-qualcomm-sm8750.litertlm

Add whisper-base.en int8: base.en-tokens.txt

Add whisper-base.en int8: base.en-decoder.int8.onnx.gz

Add whisper-base.en int8: base.en-encoder.int8.onnx.gz

Add SenseVoice Small int8 STT: model.int8.onnx.gz

Add SenseVoice Small int8 STT: tokens.txt

Add SenseVoice Small int8 STT: model.int8.onnx.gz

Add gzip-compressed Whisper Tiny.en int8: tiny.en-decoder.int8.onnx.gz

Add gzip-compressed Whisper Tiny.en int8: tiny.en-encoder.int8.onnx.gz

Upload chatterbox-turbo/speech_encoder_q4f16.onnx with huggingface_hub

Upload chatterbox-turbo/conditional_decoder_q4f16.onnx with huggingface_hub

Upload chatterbox-turbo/language_model_q4f16.onnx with huggingface_hub

Add Moonshine Tiny quantized ORT: tokens.txt

Add Moonshine Tiny quantized ORT: decoder_model_merged.ort.gz

Add Moonshine Tiny quantized ORT: encoder_model.ort.gz

Fix tokenizer.onnx: output_id INT64→INT32 (matches ORT Extensions kernel)

Compress all model/voice files with gzip (~8.5x for voices, ~35% for ONNX)

Compress all model/voice files with gzip (~8.5x for voices, ~35% for ONNX)

Compress all model/voice files with gzip (~8.5x for voices, ~35% for ONNX)

Add voice karen.wav (Chatterbox Turbo custom)

Add voice jade.wav (Chatterbox Turbo custom)

Add voice honey.wav (Chatterbox Turbo custom)

Add preprocessor_config.json (Chatterbox Turbo q4f16)

Add generation_config.json (Chatterbox Turbo q4f16)

Add config.json (Chatterbox Turbo q4f16)

Add tokenizer.json (Chatterbox Turbo q4f16)

Add embed_tokens_q4f16.onnx_data (Chatterbox Turbo q4f16)

Add embed_tokens_q4f16.onnx (Chatterbox Turbo q4f16)

Add conditional_decoder_q4f16.onnx_data (Chatterbox Turbo q4f16)