Search Results for "model-builder"

OpenAI Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification. A Transformer sequence-to-sequence model is trained on various speech processing tasks, including multilingual speech recognition, speech translation, spoken language identification, and voice activity detection.

...The repo is aimed at pushing practical multilingual ASR—robust to accents, code-switching, and domain shifts—rather than language-by-language systems. For practitioners, it’s a starting point to study transfer, zero-shot behavior, and trade-offs between model size, compute cost, and coverage.

...Training Data is the art of supervising machines through data. This includes the activities of annotation, which produces structured data; ready to be consumed by a machine learning model. Annotation is required because raw media is considered to be unstructured and not usable without it. That’s why training data is required for many modern machine learning use cases including computer vision, natural language processing and speech recognition.

Kaldi is an open source toolkit for speech recognition research. It provides a powerful framework for building state-of-the-art automatic speech recognition (ASR) systems, with support for deep neural networks, Gaussian mixture models, hidden Markov models, and other advanced techniques. The toolkit is widely used in both academia and industry due to its flexibility, extensibility, and strong community support. Kaldi is designed for researchers who need a highly customizable environment to...

...Each collection consists of prebuilt modules that include everything needed to train on your data. Every module can easily be customized, extended, and composed to create new conversational AI model architectures. Conversational AI architectures are typically large and require a lot of data and compute for training. NeMo uses PyTorch Lightning for easy and performant multi-GPU/multi-node mixed-precision training. Supported models: Jasper, QuartzNet, CitriNet, Conformer-CTC, Conformer-Transducer, Squeezeformer-CTC, Squeezeformer-Transducer, ContextNet, LSTM-Transducer (RNNT), LSTM-CTC. ...

FireRedASR is an industrial-grade family of open-source automatic speech recognition models designed to provide high-precision speech-to-text performance across languages including Mandarin, English, and various Chinese dialects, achieving new state-of-the-art benchmarks on public test sets. The project includes multiple model variants to meet different application needs, such as high-accuracy end-to-end interaction using an encoder-adapter-LLM framework and efficient real-time recognition using attention-based encoder-decoder architectures, giving developers flexibility in balancing performance and resource constraints. FireRedASR not only excels in traditional speech recognition tasks but also demonstrates strong capability in challenging scenarios like singing lyrics recognition, where accurate transcription is often difficult for conventional models.

A subtitle generator for Japanese Adult Videos. Transformer-based ASR architectures like Whisper suffer significant performance degradation when applied to the spontaneous and noisy domain of JAV. This degradation is driven by specific acoustic and temporal characteristics that defy the statistical distributions of standard training data.

ASRT is an end-to-end deep-learning Chinese ASR system built with TensorFlow/Keras, using convolution + CTC and a Max-Entropy HMM language model. It provides a REST/gRPC server backend and client SDKs in multiple languages (Python, Java, Go, Windows). Notably lightweight, it performs well without needing GPU acceleration and runs across platforms, targeting developers and researchers building Chinese voice interfaces.