Public KG record
Qwen3-ASR-1.7B
Recorded overview
Covers 52 languages and dialects with a dedicated forced-alignment model for tim
An evidence-backed entity from the project knowledge graph; detailed tool metadata is still being added.
Recorded details
- Capabilities: speech recognition
- Integrations: safetensors integration
- Languages: 支持30种语言及22种中文方言
- License: apache-2.0
- License: Apache-2.0
- Supported types: audio input
- Supported types: text output
- Performance: 4.94%平均WER
Evidence coverage
The KG currently records 13 known information dimensions and has 6 undocumented dimensions, linked to 3 public source articles. These counts describe record coverage, not model performance or verified fit.
Related public records
- Qwen — develops
- NVIDIA Nemotron 3.5 Transcribe — outperforms
- Qwen3-ASR — part of