Model reference · open weights
whisper-th-large-combined is an open-weight audio or speech model from biodatlab. whisper-th-large-combined (BF16) weighs 6.2 GB; the smallest configuration that runs it is RTX 3060 12 GB.
For self-hosting, compare this build's requirements below with the GPU you plan to rent.
Summary of the biodatlab/whisper-th-large-combined model card, 2026-10-01
What it is
| Released by | biodatlab |
|---|---|
| Released | 2022-12-12 |
| VRAM | 6.2 GB for the weights |
What it runs on
| Card | One stream | Memory |
|---|---|---|
| RTX 3060 12 GB | fits | 11.6 GB |
| RTX 4060 Ti 16 GB | fits | 15.4 GB |
| RTX 3090 24 GB | fits | 23.4 GB |
| RTX 4090 24 GB | fits | 23.4 GB |
| RTX 5090 32 GB | fits | 31.0 GB |
| L40S 48 GB | fits | 44.0 GB |
| A100 80 GB | fits | 78.2 GB |
| H100 80 GB | fits | 78.1 GB |
| RTX PRO 6000 Blackwell 96 GB | fits | 93.8 GB |
| DGX Spark (GB10) 128 GB unified | fits | 107 GB |
| H200 141 GB | fits | 138 GB |
| B200 180 GB | fits | 176 GB |
From the model card
This model is a fine-tuned version of openai/whisper-large-v2 on the mozilla-foundation/common_voice_11_0 th dataset. It achieves the following results on the evaluation set:
More information needed
More information needed
More information needed
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1845 | 1.05 | 5000 | 0.1244 | 15.5103 |
Quoted from the model card on Hugging Face. The full card is behind the Hugging Face link above.
Benchmarks
As published on the model card: the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Automatic Speech Recognition | mozilla-foundation/common_voice_11_0 th | Wer | 15.510 |