SpeechLLM: A multimodal LLM combining speech encoders with TinyLlama for joint ASR, gender, age, accent, and emotion prediction from audio.
Prosodic attention and distillation techniques to improve end-to-end SLU, achieving up to 8% intent classification accuracy gain on SLURP dataset.
Skit-S2I: The first publicly available Indian-accented SLU dataset in the banking domain for end-to-end speech-to-intent research.
Character level language model of RNN(LSTM) in PyTorch.
Emojify a sentence with NLP, flask server to emojify a sentence.
Topic Modelling for New York Times news articles for given dates using NYTimes API.
Machine Translation english to french using Seq2Seq Attention model in PyTorch.
Sentiment analysis of tweets of any topic fetched with twitter API and sentiment analysis of the tweets with NLTK.