Parler-TTS models
4 Parler-TTS models on Hugging Face, from 878M to 2.3B parameters. At the precision each one is published in, the smallest needs about 3.9 GB of VRAM (parler-tts-mini-v1, cheapest live fit: V100) and the largest about 10.4 GB (parler-tts-large-v1, cheapest live fit: V100). The cheapest way to run parler-tts-mini-v1 is $0.088/hr.
Parler-TTS models
| Model | Parameters | Published as | VRAM needed | Live GPU fit | Est. $/hr |
|---|---|---|---|---|---|
| parler-tts-mini-v1 | 878M | F32 | 3.9 GB | V100 | $0.088/hr |
| indic-parler-tts | 938M | F32 | 4.2 GB | V100 | $0.088/hr |
| parler-tts-mini-multilingual-v1.1 | 938M | F32 | 4.2 GB | V100 | $0.088/hr |
| parler-tts-large-v1 | 2.3B | F32 | 10.4 GB | V100 | $0.088/hr |
VRAM is for the precision the model is published in, with the same overhead and an 8,192-token context assumed on every page; see the methodology. The fit shown is the lowest-priced single GPU type that holds the model at that precision, or the lowest-priced multi-GPU set (up to 8) when none does.
