whisper-th-medium-combined

biodatlab/whisper-th-medium-combined

Speech Recognition817M parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
3,690
Total downloads
123.5K
Gained 7D
+648(increase)
0.5%(up) vs baseline
Gained 30D
—
Likes
20
+0 in 7D
Rank · tracked models
#14,146
73(down 73 places)this week
Parameters
817M
Last source update
Feb 20, 2024
Momentum
48.1
  • whisper-th-medium-combined gained 648 downloads during the last seven tracked days.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

whisper-th-medium-combined is a speech recognition model published by biodatlab. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 32h ago.

Published
Dec 14, 2022
Last updated
Feb 20, 2024
Library
transformers
License
apache-2.0
Task
Speech Recognition
Parameters
816,967,680
Spaces
—
Derivative models
—
Velocity 7D/day
93
transformerssafetensorswhisperautomatic-speech-recognitionwhisper-eventgenerated_from_trainerthdataset:mozilla-foundation/common_voice_13_0dataset:google/fleursbase_model:openai/whisper-mediumbase_model:finetune:openai/whisper-mediumdoi:10.57967/hf/0227

Publisher

biodatlabView publisher statistics →

Derived from openai/whisper-medium (reported by the source; parent not yet tracked).

Similar models

Models similar to whisper-th-medium-combined
ModelDL 30D
kb-whisper-mediumKBLab2,003
whisper-medium-quantized.w8a8RedHatAI29
canary-1b-flashnvidia3,871
CrisperWhisper2.0_turbonyralabs8,735
paza-whisper-large-v3-turbomicrosoft749
Whisper-Large-v3-turbo-STT-Zeroth-KO-v2o0dimplz0o308