GitHub · Python
fufuchiu/speechloom
End-to-end speech model research: waveform encoding, causal decoding, codec tokens, joint losses and streaming.
- Stars
- 31
- Forks
- 172
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: audio, end-to-end-learning, python, pytorch, speech-language-model, streaming
Latest data point: Nov 22, 2026 · 31 stars · 172 forks