OpenThai2.0-ASR-Streaming

iapp/OpenThai2.0-ASR-Streaming

Speech RecognitionnemoLicense: other
Tracked by OpenModelStats since November 10, 2026View on Hugging Face ↗
Downloads 30D
1,448
Total downloads
1,448
Gained 7D
—
Gained 30D
—
Likes
11
Rank · tracked models
#36,180
8585(up 8585 places)this week
Parameters
—
Last source update
Nov 14, 2026
  • It moved from #981 to #760 among tracked Speech Recognition models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

OpenThai2.0-ASR-Streaming is a speech recognition model published by iapp. OpenModelStats has tracked the model since Nov 10, 2026, most recently observing it 8h ago.

Published
Nov 10, 2026
Last updated
Nov 14, 2026
Library
nemo
License
other
Task
Speech Recognition
Parameters
—
Spaces
—
Derivative models
—
Velocity 7D/day
—
nemoautomatic-speech-recognitionspeechstreamingThaiFastConformerTransducerNeMoNemotronthenarxiv:2509.18722

Publisher

iappView publisher statistics →

Derived from nvidia/nemotron-3.5-asr-streaming-0.6b (reported by the source; parent not yet tracked).

Similar models

Models similar to OpenThai2.0-ASR-Streaming
ModelDL 30D
whisperkit-coremlargmaxinc84.3M
wav2vec2-large-xlsr-53-japanesejonatasgrosman15.5M
faster-whisper-smallSystran6.5M
speaker-diarization-3.1pyannote6.2M
whisper-baseopenai5.9M
speaker-diarization-community-1pyannote4.9M
iapp/OpenThai2.0-ASR-Streaming — Downloads, Growth & Stats | OpenModelStats