DNN Custom Models for Speech Recognition: Model 1: CNN + RNN + TimeDistributed Dense Then I requested support of IIT Madras, Speech Lab who kindly granted access to their Voice database. But I found it is insufficient to train such a heavy model. You can also record your own audio or let the ebook reader apps read a document. Indic TTS Project: Downloaded 50+ GB of Indic TTS voice DB from Speech and Music Technology Lab, IIT Madras, which comprises of 10000+ spoken sentences from 20+ states (both Male and Female native speakers) Training_Instructions.docx: Instructions to train DeepSpeech model.DeepSpeech_Training.ipynb: Retraining of DeepSpeech Model with Indian Accent Voice Data. vui_notebook.ipynb: DNN Custom Models and Comparative Analysis to make a custom Speech Recognition model.If you run into issue while loading the pre-trained model, then it is mostly due to your deepspeech version. !deepspeech -model speech/output_graph.pbmm -lm speech/lm.binary -trie speech/trie -audio /content/06_M_artic_01_004.wav
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |