Downloads · 30 days
17
14% of all-time downloads
zen3-asr-aligner
zenlm/zen3-asr-aligner
zen3-asr-aligner is a automatic speech recognition model from zenlm. Use it when you need speech turned into text. It is set up for transformers. The card lists the license as apache-2.0.
Forced-alignment companion to Zen3 ASR. Produces word- and phoneme-level time alignments for transcripts (subtitle sync, dataset curation, dubbing). The config declares support for 11 languages.
All-time downloads
119
Public
Parameters
918M
1.8 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.8 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- transformers
- License
- apache-2.0
- Model type
- qwen3_asr
- Access
- Public
- Created
- May 30, 2026
- Updated
- Jul 14, 2026
- SHA
- e4288559
Base models
Model card
From the Hugging Face model README
Zen3 ASR Forced Aligner
Forced-alignment companion to Zen3 ASR. Produces word- and phoneme-level time alignments for transcripts (subtitle sync, dataset curation, dubbing). The config declares support for 11 languages.
Derived by fine-tuning Qwen/Qwen3-ForcedAligner-0.6B (Alibaba Cloud, Apache-2.0).
- Architecture:
Qwen3ASRForConditionalGeneration(qwen3_asr) - Parameters: ~0.6B
- Base model:
Qwen/Qwen3-ForcedAligner-0.6B
Weights
This repository contains the model weights: model.safetensors, config and tokenizer files.
The model uses the qwen3_asr architecture and loads with transformers (>= 4.57). It is API-compatible with the upstream base — follow the inference recipe on the base model card Qwen/Qwen3-ForcedAligner-0.6B.
Provenance
Fine-tuned from Qwen/Qwen3-ForcedAligner-0.6B (Apache-2.0). See NOTICE for full attribution.
- Task
- Automatic Speech Recognition
- Library
- transformers
- Type
- qwen3_asr
- License
- apache-2.0
- Languages
- en, zh
- Created
- May 30, 2026
- Updated
- Jul 14, 2026