Automatic Speech Recognition
Transformers
Safetensors
qwen3_asr
qwen3
forced-alignment
word-timestamps
multilingual
subtitle-alignment
robust-alignment
code-switching
Instructions to use fengjay01/Qwen3-ForcedAligner-Ultra with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fengjay01/Qwen3-ForcedAligner-Ultra with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="fengjay01/Qwen3-ForcedAligner-Ultra")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("fengjay01/Qwen3-ForcedAligner-Ultra") model = AutoModelForMultimodalLM.from_pretrained("fengjay01/Qwen3-ForcedAligner-Ultra", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from fengjay01/Qwen3-ForcedAligner-Ultra: direct link, hf CLI and curl.
- Browser
- Download file 357 Bytes
-
https://huggingface.co/fengjay01/Qwen3-ForcedAligner-Ultra/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://fengjay01/Qwen3-ForcedAligner-Ultra/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/fengjay01/Qwen3-ForcedAligner-Ultra/resolve/main/preprocessor_config.json
357 Bytes
| { | |
| "chunk_length": 30, | |
| "dither": 0.0, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 128, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "n_samples": 480000, | |
| "nb_max_frames": 3000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "processor_class": "Qwen3ASRProcessor", | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000 | |
| } | |