microsoft / SpeechT5

Unified-Modal Speech-Text Pre-Training for Spoken Language Processing
MIT License
1.09k stars 113 forks source link

Missing speecht5 task #37

Closed maximerenou closed 1 year ago

maximerenou commented 1 year ago

Hello,

The following Inference instructions seem outdated : https://github.com/microsoft/SpeechT5/tree/main/SpeechT5#inference-1

The script SpeechT5/scripts/generate_speech.py trigger this error when using --task speecht5 :

generate_speech.py: error: argument --task: invalid choice: 'speecht5' (choose from 'hubert_pretraining', 'denoising', 'multilingual_denoising', 'translation', 'multilingual_translation', 'translation_from_pretrained_bart', 'translation_lev', 'language_modeling', 'speech_to_text', 'legacy_masked_lm', 'online_backtranslation', 'simul_speech_to_text', 'simul_text_to_text', 'audio_pretraining', 'semisupervised_translation', 'sentence_prediction', 'cross_lingual_lm', 'translation_from_pretrained_xlm', 'masked_lm', 'sentence_ranking', 'translation_multi_simple_epoch', 'multilingual_masked_lm', 'dummy_lm', 'dummy_masked_lm', 'dummy_mt')

Thanks

mechanicalsea commented 1 year ago

Hi, @maximerenou

It seems that the task of "speecht5" is not included in fairseq.tasks. It can be solved by adding ${USER_DIR} to --user-dir, where ${USER_DIR} is the path to speecht5 code.

Wish it helpful.