| FireRedASR-AED |
- Word Error Rate (WER)
- 0.55
- Params(M)
- 1,100
|
FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration
2025-01-24 |
코드 1 |
| Seed-ASR |
- Word Error Rate (WER)
- 0.68
|
Seed-ASR: Understanding Diverse Speech and Contexts with LLM-based Speech Recognition
2024-07-05 |
연결 없음 |
| Qwen-Audio |
- Word Error Rate (WER)
- 1.29
|
Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models
2023-11-14 |
코드 1 · 코드 2 |
| MMSpeech With LM |
- Word Error Rate (WER)
- 1.9
|
MMSpeech: Multi-modal Multi-task Encoder-Decoder Pre-training for Speech Recognition
2022-11-29 |
코드 1 |
| Paraformer-large |
- Word Error Rate (WER)
- 1.95
- Params(M)
- 220
|
FunASR: A Fundamental End-to-End Speech Recognition Toolkit
2023-05-18 |
코드 1 |
| Zipformer+CR-CTC (no external language model) |
- Word Error Rate (WER)
- 4.02
- Params(M)
- 66.2
|
CR-CTC: Consistency regularization on CTC for improved speech recognition
2024-10-07 |
코드 1 |
| Lightweight Transducer With LM |
- Word Error Rate (WER)
- 4.03
- Params(M)
- 45.3
|
Lightweight Transducer Based on Frame-Level Criterion
2024-09-05 |
코드 1 |
| SE-WSBO With LM |
- Word Error Rate (WER)
- 4.1
- Params(M)
- 46
|
Improving Mandarin Speech Recogntion with Block-augmented Transformer
2022-07-24 |
코드 1 · 코드 2 |
| CIF-HKD With LM |
- Word Error Rate (WER)
- 4.1
- Params(M)
- 47
|
Knowledge Transfer from Pre-trained Language Models to Cif-based Speech Recognizers via Hierarchical Distillation
2023-01-30 |
코드 1 · 코드 2 |
| Lightweight Transducer |
- Word Error Rate (WER)
- 4.31
- Params(M)
- 45.3
|
Lightweight Transducer Based on Frame-Level Criterion
2024-09-05 |
코드 1 |
| UMA |
- Word Error Rate (WER)
- 4.7
- Params(M)
- 44.7
|
Unimodal Aggregation for CTC-based Speech Recognition
2023-09-15 |
코드 1 |
| U2 |
- Word Error Rate (WER)
- 4.72
- Params(M)
- 47
|
Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition
2020-12-10 |
코드 1 · 코드 2 · 코드 3 · 코드 4 · 코드 5 |
| Paraformer |
- Word Error Rate (WER)
- 4.95
- Params(M)
- 46.3
|
FunASR: A Fundamental End-to-End Speech Recognition Toolkit
2023-05-18 |
코드 1 |
| BAT |
- Word Error Rate (WER)
- 4.97
- Params(M)
- 90
|
BAT: Boundary aware transducer for memory-efficient and low-latency ASR
2023-05-19 |
코드 1 |
| CTC-CRF 4gram-LM |
- Word Error Rate (WER)
- 6.34
|
CAT: A CTC-CRF based ASR Toolkit Bridging the Hybrid and the End-to-end Approaches towards Data Efficiency and Low Latency
2020-05-27 |
코드 1 |
| BRA-E |
- Word Error Rate (WER)
- 6.63
- Params(M)
- 8.5
|
Beyond Universal Transformer: block reusing with adaptor in Transformer for automatic speech recognition
2023-03-23 |
연결 없음 |
| CTC/Att |
- Word Error Rate (WER)
- 6.7
|
A Comparative Study on Transformer vs RNN in Speech Applications
2019-09-13 |
코드 1 · 코드 2 |
| Att |
- Word Error Rate (WER)
- 18.7
|
End-to-end Speech Recognition with Adaptive Computation Steps
2018-08-30 |
연결 없음 |