checklist.day

Wav2Vec2 XLS-R 300M FTSpeech

JSON →
saattrupdan audio
audio

A fine-tuned XLS-R 300M model for speech recognition on the FTSpeech dataset.

Capabilities

streaming

Dates

releasedMar 2023

Resources

homepagehuggingface.co/saattrupdan/wav2vec2-xls-r-300m-ftspeech ↗

API

full doc /v1/models/saattrupdan/wav2vec2-xls-r-300m-ftspeech