Model reference · open weights
speecht5_finetuned_iamwille_ig is an open-weight audio or speech model from iamwille, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
should probably proofread and complete it, then remove this comment. -- speecht5finetunediamwilleig This model is a fine-tuned version of microsoft/speecht5tts on an unknown dataset. It achieves the following results on the evaluation set: - Loss: 0.4255 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: - learningrate: 0.0001 - trainbatchsize: 4 - evalbatchsize: 2 - seed: 42 - gradientaccumulationsteps: 8 - totaltrainbatchsize: 32 - optimizer: Use OptimizerNames.ADAMWTORCHFUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizerargs=No additional optimizer arguments - lrschedulertype: linear - lrschedulerwarmupsteps: 100 - trainingsteps: 5000 Training results Framework versions - Transformers 5.15.1 - Pytorch 2.13.0 - Datasets 5.0.1 - Tokenizers 0.22.2
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | iamwille |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 144M |
| Variants | 1 |
| Runs with | transformers |
| Based on | microsoft/speecht5_tts |
| Released | 2026-08-19 |
| Popularity | 759 downloads / month |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| speecht5_finetuned_iamwille_ig | 144M | BF16 | ~0.3 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys speecht5-finetuned-iamwille-ig for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (speecht5-finetuned-iamwille-ig 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="speecht5-finetuned-iamwille-ig" -F file=@audio.mp3
Details
Tags
Licence
Open weights under mit — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗