Models / meta / Wav2Vec2 XLSR-53 eSpeak CV FT

Wav2Vec2 XLSR-53 eSpeak CV FT

JSON →
metaaudio

A fine-tuned Wav2Vec2 model for cross-lingual speech recognition using eSpeak phoneme labels and Common Voice data.

audiotext
Specs
Context & limits
context window
max output
Lifecycle
Dates
released2021-08-01
Resources