Basis-Begriffe rund um Large Language Models.
Computational method in transformer models that weights which parts of the input text are most relevant for predicting the next token — instead of treating every part as equally important.
Audio normalization is the adaptive linear scaling of an audio signal to a target level — the tool first measures a reference value (peak, RMS or LUFS) and from that calculates the required gain.
Automatic Speech Recognition (ASR), also called Speech-to-Text (STT), is the automatic conversion of spoken language into written text by an acoustic model.
The context window is the maximum number of tokens a language model can process at once — input and output combined.
Three related concepts for digital audio levels: dBFS is the scale with 0 dBFS as the hard ceiling, headroom is the safety margin below the maximum, clipping is the hard cut-off when a signal exceeds it.
An embedding is a numeric representation (vector) of text, an image, or other data in which semantically similar content sits close together in space.
A hallucination is a language-model response that sounds plausible but is factually wrong or fabricated — typically caused by statistical guessing without a factual anchor.
Inference is the act of running an already-trained model to turn an input into a response — production use, not training.
The KV cache (key-value cache) stores the already computed key and value vectors of a language model's attention layers during text generation. This avoids recomputing the entire context for each new token and significantly speeds up inference.
LLM stands for Large Language Model — a neural network trained on large volumes of text to interpret and generate natural language.
A model card is a standardised datasheet for an AI model — documenting purpose, training data, performance, limitations and ethical considerations in one place.
Path dependency describes how, during LLM generation, each early token shapes everything that follows — the first verbalized finding steers the entire remaining analysis in one direction.
RAG (Retrieval-Augmented Generation) connects a language model to an external knowledge source — relevant passages are retrieved and passed to the model alongside the question.
Reasoning Effort is a control parameter on modern reasoning models that sets how much internal step-by-step thinking (thinking tokens) a model spends before answering — higher levels raise quality but also latency and cost.
Safetensors is a file format developed by Hugging Face for storing model weights — faster, safer and more language-agnostic than the older PyTorch `.pt`/`.bin` format.
Sampling is the weighted drawing of the next token from a language model's probability distribution — governed by temperature, top-p and top-k. It produces the variability between two runs.
Stop sequences are strings that make an LLM end token generation as soon as they appear. They constrain the output deliberately — to prevent role switches, format markers or overly long answers.
Temperature is a sampling parameter that controls how deterministic or creative a language model's responses are — low values stay conservative, high values produce more variety.
The thinking budget (token budget) is the maximum number of internal reasoning tokens a reasoning model may spend on "thinking" per request — controlling the trade-off between answer depth and cost or latency.
A token is the smallest unit a language model works with internally — usually a sub-word fragment, occasionally a single character.
A tokenizer is the program that splits text into tokens before a language model can process it — it determines how many tokens a piece of text costs.
Top-p (nucleus sampling) and top-k are sampling strategies for LLMs that decide which token candidates to draw from at each step — together with temperature they control the creativity of the output.
Whisper is OpenAI's open speech-to-text model from 2022 — a multilingual encoder-decoder transformer that turns audio into text and ships in several sizes under an MIT license.