top | item 46905056 Sopro v1.5: A 135M TTS model trained for ~$100, runs 20× real-time on CPU 5 points| sammyyyyyyy | 24 days ago |huggingface.co 1 comment order hn newest sammyyyyyyy|24 days ago Today, I'm releasing a new version of my side project: SoproTTSA 135M parameter TTS model trained for ~$100 on 1 GPU, running ~20× real-time on a base MacBook M3 CPU.v1.5 highlights (on CPU):• 250 ms TTFA streaming latency • 0.05 RTF (~20× real-time) • Zero-shot voice cloning • Smaller, faster, more stableStill not perfect (OOD voices can be tricky, and there are still some artifacts), but a decent upgrade.Repo: https://github.com/samuel-vitorino/sopro
sammyyyyyyy|24 days ago Today, I'm releasing a new version of my side project: SoproTTSA 135M parameter TTS model trained for ~$100 on 1 GPU, running ~20× real-time on a base MacBook M3 CPU.v1.5 highlights (on CPU):• 250 ms TTFA streaming latency • 0.05 RTF (~20× real-time) • Zero-shot voice cloning • Smaller, faster, more stableStill not perfect (OOD voices can be tricky, and there are still some artifacts), but a decent upgrade.Repo: https://github.com/samuel-vitorino/sopro
sammyyyyyyy|24 days ago
A 135M parameter TTS model trained for ~$100 on 1 GPU, running ~20× real-time on a base MacBook M3 CPU.
v1.5 highlights (on CPU):
• 250 ms TTFA streaming latency • 0.05 RTF (~20× real-time) • Zero-shot voice cloning • Smaller, faster, more stable
Still not perfect (OOD voices can be tricky, and there are still some artifacts), but a decent upgrade.
Repo: https://github.com/samuel-vitorino/sopro