Instructions to use FluidVoice-Labs/fluid-speech-pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use FluidVoice-Labs/fluid-speech-pro with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("FluidVoice-Labs/fluid-speech-pro") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Fluid Speech Pro
A speech-to-text model for English and the 24 other European languages of Parakeet v3, from the team behind FluidVoice. The full model card is coming soon.
Load it with NVIDIA NeMo and fluid_speech.py from this repository:
fluid_speech.load("FluidVoice-Labs/fluid-speech-pro"), or fluid_speech.load("FluidVoice-Labs/fluid-speech-pro", clean_mode=True)
for clean mode, which removes repeated words and filler words.
License and attribution
CC BY 4.0. If you use the model, please credit it as Fluid Speech Pro by FluidVoice.
Built on NVIDIA Parakeet TDT 0.6B v3 and Moondream Parakeet Ultra, both CC BY 4.0.
- Downloads last month
- 8
Model tree for FluidVoice-Labs/fluid-speech-pro
Base model
moondream/parakeet-ultra