Open-weight model
whisper-medium_mucs_62901_ratio_alldata_lr_1e-4_lgid_None_hinglish_mixed_scripts_FT
by Diana Davidson dianavdavidson/whisper-medium_mucs_62901_ratio_alldata_lr_1e-4_lgid_None_hinglish_mixed_scripts_FT
whisper-medium_mucs_62901_ratio_alldata_lr_1e-4_lgid_None_hinglish_mixed_scripts_FT is an open-weight model from Diana Davidson. It has 764M parameters. At 16-bit it needs about 1.8 GB of GPU memory, which fits on 1x MI300X from $1.85 an hour, at the lowest prices in the SAVRN Index. It draws 44 downloads a month.
Runs On
What it takes to serve whisper-medium_mucs_62901_ratio_alldata_lr_1e-4_lgid_None_hinglish_mixed_scripts_FT (764M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 1.5 GB | 1.8 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.8 GB | 0.9 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.4 GB | 0.5 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
Model Card
The publisher has not written a card for this model.
Configuration
- Architecture
- WhisperForConditionalGeneration
- Layers
- 24
- Vocabulary size
- 51,865
- Model type
- whisper
Identity and Version
- Repository
- dianavdavidson/whisper-medium_mucs_62901_ratio_alldata_lr_1e-4_lgid_None_hinglish_mixed_scripts_FT
- Publisher
- Diana Davidson
- Task
- Not stated by the source
- Modality
- Other
- Library
- Not stated by the source
- Parameters
- 764M parameters
- Languages
- Not stated by the source
- Revision
- af4b0504c3c06920bc5558f323939700ca93d1af
- First published
- 2026-09-16
- Last updated
- 2026-09-18
Files and Weights
8 files, 3.1 GB in total. The weights are 2 files totalling 3.1 GB in bin, safetensors.
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 3.1 GB | 4f73f3491ed2 |
| training_args.bin | Weights | 5.5 KB | 61ce5cd43701 |
| config.json | Configuration | 1.3 KB | — |
| generation_config.json | Configuration | 4.5 KB | — |
| processor_config.json | Configuration | 409 B | — |
| .gitattributes | Repository | 1.5 KB | — |
| tokenizer.json | Tokenizer | 3.9 MB | — |
| tokenizer_config.json | Tokenizer | 2.1 KB | — |
License and Download
- License
- Not stated by the source
- Access
- Open weights, no gate
- Download size
- 3.1 GB
Released by Diana Davidson through its official repository on Hugging Face.
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 3.1 GB |
| 16-bit | 1.5 GB |
| 8-bit | 0.8 GB |
| 4-bit | 0.4 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About whisper-medium_mucs_62901_ratio_alldata_lr_1e-4_lgid_None_hinglish_mixed_scripts_FT
How much GPU memory does whisper-medium_mucs_62901_ratio_alldata_lr_1e-4_lgid_None_hinglish_mixed_scripts_FT need?
About 1.8 GB at 16-bit and 0.5 GB at 4-bit: the weights (764M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run whisper-medium_mucs_62901_ratio_alldata_lr_1e-4_lgid_None_hinglish_mixed_scripts_FT on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.