ESPnet-SpeechLM: An Open Speech Language Model Toolkit
This toolkit democratizes speech language model development for researchers and practitioners, though it is incremental as it builds on existing frameworks.
The authors tackled the challenge of developing speech language models by introducing ESPnet-SpeechLM, an open toolkit that standardizes speech processing tasks as universal sequential modeling problems, resulting in a 1.7B-parameter model pre-trained on text and speech tasks across diverse benchmarks.
We present ESPnet-SpeechLM, an open toolkit designed to democratize the development of speech language models (SpeechLMs) and voice-driven agentic applications. The toolkit standardizes speech processing tasks by framing them as universal sequential modeling problems, encompassing a cohesive workflow of data preprocessing, pre-training, inference, and task evaluation. With ESPnet-SpeechLM, users can easily define task templates and configure key settings, enabling seamless and streamlined SpeechLM development. The toolkit ensures flexibility, efficiency, and scalability by offering highly configurable modules for every stage of the workflow. To illustrate its capabilities, we provide multiple use cases demonstrating how competitive SpeechLMs can be constructed with ESPnet-SpeechLM, including a 1.7B-parameter model pre-trained on both text and speech tasks, across diverse benchmarks. The toolkit and its recipes are fully transparent and reproducible at: https://github.com/espnet/espnet/tree/speechlm.