GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
techiaith
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
techiaith
Model Tree
openai/whisper-large-v2
Input Modalities
Output Modalities
Supported Functionality
| Task | Description |
|---|---|
| Welsh transcription | Welsh audio → Welsh text |
| English transcription | English audio (UK/Irish accents) → English text |
| Welsh→English translation (experimental) | Welsh audio → English text — limited quality, not recommended for production (see below) |
WER / CER (lower is better) on the held-out benchmark. Average across the 4 transcription test sets: WER 20.29, CER 7.33.
| Test Set | WER | CER |
|---|---|---|
| cymen-arfor/lleisiau-arfor (spontaneous) | 29.20 | 11.59 |
| techiaith/banc-trawsgrifiadau-bangor (mixed) | 26.71 | 9.91 |
| techiaith/commonvoice-23-0-cy (read) | 15.10 | 4.35 |
| Test Set | WER | CER |
|---|---|---|
| techiaith/commonvoice-23-0-en/GB-IE (read, UK/Irish) | 10.16 | 3.47 |
The model can translate Welsh speech directly into English text (task="translate"). This capability is experimental and has not been formally evaluated; its translation quality is limited and it is not recommended for production use.
For higher-quality English, transcribe the Welsh audio with this model and translate the resulting Welsh text with a dedicated Welsh→English machine translation model.
| Dataset | Language | Split | Revision |
|---|---|---|---|
| techiaith/banc-trawsgrifiadau-bangor | Welsh | train | 26.07 |
| techiaith/corpws-clllc-wlga | Welsh | clips | 5d00294c31 |
| Parameter | Value |
|---|---|
| Base model | openai/whisper-large-v2 |
| Learning rate | 1e-05 |
| LR scheduler | cosine |
| Warmup steps | 500 |
| Max steps | 15000 |
| Weight decay | 0.01 |
| Batch size | 16 × 2 accumulation × 2 GPUs = 64 effective |
| FP16 | True |
| SpecAugment | True |
python
from transformers import pipelinepipe = pipeline("automatic-speech-recognition",model="techiaith/whisper-large-ft-cy-en",)# Welsh transcriptionresult = pipe("welsh_audio.wav", generate_kwargs={"language": "cy", "task": "transcribe"})# English transcriptionresult = pipe("english_audio.wav", generate_kwargs={"language": "en", "task": "transcribe"})# Welsh to English translationresult = pipe("welsh_audio.wav", generate_kwargs={"language": "cy", "task": "translate"})
A CTranslate2 (int8 quantised) version is available at techiaith/whisper-large-ft-cy-en-ct2 for faster inference.
Developed by Uned Technolegau Iaith, Prifysgol Bangor / Language Technologies Unit, Bangor University.
Funded by the Welsh Government.
| techiaith/commonvoice_23_0_cy | Welsh | train+dev[50%:] | main |
| cymen-arfor/lleisiau-arfor | Welsh | train | main |
| techiaith/commonvoice_vad_cy | Welsh | train | main |
| techiaith/commonvoice_23_0_en__GB_IE | English | train[:10%] | main |
| techiaith/commonvoice_23_0_cy_en | Welsh | train[:10%] | main |
| Curation applied | True |
| Early stopping patience | 10 |
| Selection metric | eval_btb_wer |