ComfyUI-Qwen3-ASR

Qwen3ASRTranscriber

The Qwen3 ASR Transcriber is the primary inference node for the Qwen3-ASR model family. It converts speech from audio input into text and can optionally generate precise word-level timestamps when paired with a forced aligner. - audio: The input audio stream (usually from a Load Audio node). - modelname: The directory name of the Qwen3-ASR model (0.6B or 1.7B) located in models/diffusionmodels/Qwen3-ASR/. - language: The target language for transcription. Use auto to allow the model to automatically identify the spoken language. - device: The hardware device to run the model on (cuda or cpu). - precision: The floating-point precision. bf16 is recommended for modern NVIDIA GPUs to save VRAM without losing accuracy. - maxnewtokens: The maximum number of tokens to generate in the output text. Increase this for longer audio files. - flashattention2: Enable Flash Attention 2 for faster inference and lower VRAM usage. Requires a compatible NVIDIA GPU and the flash-attn package installed. - chunksize: Process audio in chunks of this many seconds (default: 30). Set to 0 to disable. This is critical for transcribing long audio files to prevent the model from exceeding its context window. - overlap: The number of seconds of overlap between chunks (default: 2). This helps maintain context and prevents words from being cut off at chunk boundaries. - forcedaligner (Optional): An optional input from the Qwen3 Forced Aligner Config node. If connected, the node will calculate and output word-level timestamps. - text: The raw transcription of the audio. - timestamps: A formatted string con…

Qwen3 ASR · 2 outputs

Qwen3ForcedAlignerConfig

The Qwen3 Forced Aligner Config node is a helper node used to initialize the Qwen3-ForcedAligner-0.6B model. This configuration is required if you want the Qwen3 ASR Transcriber to output word-level timestamps. - modelname: The directory name of the Forced Aligner model located in models/diffusionmodels/Qwen3-ASR/. - device: The hardware device to run the aligner on. This should generally match the device used by the Transcriber node. - precision: The floating-point precision for the aligner model. - flashattention2: Enable Flash Attention 2 for the aligner model to improve performance and reduce memory footprint. - alignerconfig: A configuration object that bundles the model path and loading arguments. Connect this to the forcedaligner input of the Qwen3 ASR Transcriber. Standard ASR models generate text but often lack precise timing for when each word was spoken. The Forced Aligner is a specialized model that takes the generated text and the original audio to "align" them, providing highly accurate start and end times for every word. Ensure you have downloaded the Qwen3-ForcedAligner-0.6B model into your models/diffusionmodels/Qwen3-ASR/ folder.

Qwen3 ASR · 1 output