Model reference · open weights
whisper-large is an open-weight audio or speech model from metythorn. 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 by | metythorn |
|---|---|
| Type | Audio & music |
| Task | Speech→text |
| Parameters (lead) | 1.5B |
| Released | 2025-11-21 |
| Popularity | 4k downloads / month |
| Licence | Open weights |
About
Fine-tuned variant of openai/whisper-large-v3 for Khmer automatic speech recognition. The model was trained with the utilities in whisper and is intended for transcription workloads that prioritize Khmer text normalization, including numerals, currency, and date expressions.
| Attribute | Value |
|---|---|
| Base model | openai/whisper-large-v3 |
| Language | Khmer (km-KH) |
| Task | Automatic Speech Recognition (speech-to-text) |
| Sample rate | 16 kHz audio, automatically resampled |
| Input length | Up to 30 s clips (truncated during batching) |
| Finetuning data | asr_mixed_dataset.txt (internal manifests, normalized through dataset_builder.segment_text) |
| Epochs | 10 |
| Batch size | 2 (gradient accumulation 1) |
| Optimizer | AdamW (managed by Seq2SeqTrainer) |
| Learning rate | 1e-6 with cosine scheduler & 1k warmup steps |
| Normalization | Khmer-specific regex and rule-based normalization (khmerspeech, khmercut) |
| Dataset | Training with Mixed Khmer & English audio with 199K samples (225 hours), train all khmer public dataset + humaned label dataset |
| Training Time | Training with Mixed precision with RTX-5090 VRAM 32GB for 10 days |
Limitations: performance has been validated only on internal validation/test splits. Long-form audio, accents outside the training distribution, or noisy backgrounds may degrade accuracy.
import torch
import torchaudio
from transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline
AUDIO_PATH = "audio_path.wav"
device = "cuda:0" if torch.cuda.is_available() else "cpu"
torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32
model_id = "metythorn/whisper-large-v3"
model = AutoModelForSpeechSeq2Seq.from_pretrained(
model_id,
torch_dtype=torch_dtype,
low_cpu_mem_usage=True,
use_safetensors=True,
)
model.to(device)
processor = AutoProcessor.from_pretrained(model_id)
pipe = pipeline(
task="automatic-speech-recognition",
model=model,
tokenizer=processor.tokenizer,
feature_extractor=processor.feature_extractor,
torch_dtype=torch_dtype,
device=device,
)
speech_waveform, sr = torchaudio.load(AUDIO_PATH)
# Whisper expects 16kHz mono
if sr != 16000:
speech_waveform = torchaudio.functional.resample(
speech_waveform,
orig_freq=sr,
new_freq=16000
)
speech_waveform = speech_waveform.squeeze().numpy()
result = pipe(speech_waveform)
print("Transcription:", result["text"])
From the published model card. Full card on the HuggingFace links in the sidebar.
Using it via the API
Once AxForge deploys metythorn-whisper-large for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (metythorn-whisper-large 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="metythorn-whisper-large" -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.