Finetuned version of KBs VoxRex large model using Swedish radio broadcasts, NST and Common Voice data. Evalutation without a language model gives the following: WER for NST + Common Voice test set (2% of total sentences) is 2.5%. WER for Common Voice test set is 8.49% directly and 7.37% with a 4-gram language model. When using this model, make sure that your speech input is sampled at 16kHz. This model has been fine-tuned for 120000 updates on NST + CommonVoice and then for an additional 20000 updates on CommonVoice only. The additional fine-tuning on CommonVoice hurts performance on the NST+CommonVoice test set somewhat and, unsurprisingly, improves it on the CommonVoice test set. It seems…
Open weights
cc0-1.0
315M parameters
transformers
Model · Tabular classification
Keras
This repo contains the model and the notebook on how to build and train a Keras model for Collaborative Filtering for Movie Recommendations. Full credits to Siddhartha Banerjee. Based on a user and movies they have rated highly in the past, this model outputs the predicted rating a user would give to a movie they haven't seen yet (between 0-1). This information can be used to find out the top recommended movies for this user. The dataset consists of user's ratings on specific movies. It also consists of the movie's specific genres. The model was trained for 5 epochs with a batch size of 64. The following hyperparameters were used during training: - trainingprecision: float32
Open weights
cc0-1.0
tf-keras
