Streaming speech translation models and frameworks
Patrick Lumbantobing
pltobing
AI & ML interests
Speech Synthesis, Voice Conversion, Speech Recognition, Speech Translation, Speech Enhancement, Speaker Diarization, Low-Latency Real-Time System, Multimodal LLM, Conversational AI, Speech-to-Speech LLM, Audio Engineering
Recent Activity
updated a model about 13 hours ago
vertox-ai/speech-text-data-aligners published a model about 16 hours ago
vertox-ai/speech-text-data-alignersOrganizations
models 9
pltobing/streaming-speech-translation
Audio-to-Audio • 4B • Updated • 14 • 8
pltobing/Qwen3-TTS-Streaming-ONNX
Text-to-Speech • Updated • 48 • 4
pltobing/MOSS-TTS-Realtime-ONNX
Text-to-Speech • Updated • 5 • 7
pltobing/nemo-asr-cache-aware-streaming-1120ms-en-onnx
Automatic Speech Recognition • Updated • 2
pltobing/nemo-asr-cache-aware-streaming-560ms-en-onnx
Automatic Speech Recognition • Updated • 1
pltobing/XTTSv2-Streaming-ONNX
Text-to-Speech • Updated • 22 • 4
pltobing/translategemma-4b-it-Q8_0-GGUF
Translation • 4B • Updated • 5
pltobing/translategemma-4b-it-Q4_K_M-GGUF
Translation • 4B • Updated • 2
pltobing/nemo-asr-cache-aware-streaming-160ms-en-onnx
Updated • 7
datasets 0
None public yet