Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Finstreder (Quartznet)

Finstreder (Quartznet)

Reported on 17 benchmarks across 5 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Speech10 results

DialogueonSnips-SmartSpeaker
Accuracy-EN (%)· 2022-06-29
77.6
best: 87.9 (Finstreder (Conformer, character-based))
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589
DialogueonSnips-SmartSpeaker
Accuracy-FR (%)· 2022-06-29
77.8
best: 86.5 (Finstreder (Conformer, character-based))
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589
DialogueonSnips-SmartLights
Accuracy (%)· 2022-06-29
84.8
best: 89 (Finstreder (Conformer, character-based))
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589
DialogueonFluent Speech Commands
Accuracy (%)· uses extra data· 2022-06-29
99.2
best: 99.8 (Finstreder (Conformer + AMT, character-based))
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589
DialogueonTimers and Such
Accuracy (%)· uses extra data· 2022-06-29
90
best: 95.4 (Finstreder (Conformer))
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589
Spoken Language UnderstandingonSnips-SmartSpeaker
Accuracy-EN (%)· 2022-06-29
77.6
best: 87.9 (Finstreder (Conformer, character-based))
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589
Spoken Language UnderstandingonSnips-SmartSpeaker
Accuracy-FR (%)· 2022-06-29
77.8
best: 86.5 (Finstreder (Conformer, character-based))
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589
Spoken Language UnderstandingonSnips-SmartLights
Accuracy (%)· 2022-06-29
84.8
best: 89 (Finstreder (Conformer, character-based))
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589
Spoken Language UnderstandingonFluent Speech Commands
Accuracy (%)· uses extra data· 2022-06-29
99.2
best: 99.8 (Finstreder (Conformer + AMT, character-based))
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589
Spoken Language UnderstandingonTimers and Such
Accuracy (%)· uses extra data· 2022-06-29
90
best: 95.4 (Finstreder (Conformer))
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589

Natural Language Processing7 results

Intent ClassificationonSLURP
Accuracy (%)· uses extra data· 2022-06-29
43.15
best: 90.07 (TDT 0-8)
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589
Slot FillingonSLURP
F1· uses extra data· 2022-06-29
0.313
best: 0.8061 (TDT 0-6)
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589
Dialogue UnderstandingonSnips-SmartSpeaker
Accuracy-EN (%)· 2022-06-29
77.6
best: 87.9 (Finstreder (Conformer, character-based))
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589
Dialogue UnderstandingonSnips-SmartSpeaker
Accuracy-FR (%)· 2022-06-29
77.8
best: 86.5 (Finstreder (Conformer, character-based))
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589
Dialogue UnderstandingonSnips-SmartLights
Accuracy (%)· 2022-06-29
84.8
best: 89 (Finstreder (Conformer, character-based))
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589
Dialogue UnderstandingonFluent Speech Commands
Accuracy (%)· uses extra data· 2022-06-29
99.2
best: 99.8 (Finstreder (Conformer + AMT, character-based))
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589
Dialogue UnderstandingonTimers and Such
Accuracy (%)· uses extra data· 2022-06-29
90
best: 95.4 (Finstreder (Conformer))
Finstreder: Simple and fast Spoken Language Understanding with Finite State Transducers using modern Speech-to-Text models arXiv:2206.14589