Automatic Speech Recognition PyTorch JAX TransformersGerman wav2vec2 audio hf-asr-leaderboard mozilla-foundation/common_voice_6_0 robust-speech-event speech xlsr-fine-tuning-week Eval Results License: apache-2.0
I saw that some fine-tuned models got tokenizer_config.json which allows loading a processor. For instance, https://huggingface.co/lighteternal/wav2vec2-large-xlsr-53-greek/tree/main has got one.
Is there any reason why this is missing here?
Hello @synapse! To be honest, I don't know why this file is missing here. But as it's working without it, it seems not necessary. I think it's 'cause there is a "special_tokens_map.json" file that replaces the "tokenizer_config.json"