Model reference · open weights

whisper-large-hy-2

Available as managed deployment Audio arampacha · community Speech→text 1 variants 1k dl/mo

whisper-large-hy-2 is an open-weight audio or speech model from arampacha. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Released byarampacha
TypeAudio & music
TaskSpeech→text
Runs withtransformers
Released2022-12-18
Popularity1k downloads / month
LicenceOpen weights

About

What whisper-large-hy-2 is

This model is a fine-tuned version of openai/whisper-large-v2 on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.1806
  • eval_wer: 19.9869
  • eval_runtime: 1358.6954
  • eval_samples_per_second: 0.292
  • eval_steps_per_second: 0.074
  • epoch: 13.33
  • step: 3000
Read the full model card

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 1e-05
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 400
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Framework versions

  • Transformers 4.26.0.dev0
  • Pytorch 1.13.1+cu117
  • Datasets 2.7.1.dev0
  • Tokenizers 0.13.2

From the published model card. Full card on the HuggingFace links in the sidebar.

Benchmarks

Reported results

As published on the model card — the maker's own numbers, not measured by AxForge.

TaskDatasetMetricScore
Automatic Speech RecognitionCommon Voice 11.0Wer19.987

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys whisper-large-hy-2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (whisper-large-hy-2 below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -F model="whisper-large-hy-2" -F file=@audio.mp3

Create an account — your API key is available in the console. 3M free tokens every 30 days with every new account.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms