GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
maleo-ai
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
maleo-ai
Model Tree
openai/whisper-small
Input Modalities
Output Modalities
Supported Functionality
WER / CER (%), full test sets, lowercase + punctuation stripped:
| Test set | whisper-small | whisper-small-id v2 | v2, short context |
|---|---|---|---|
| FLEURS id (684 utts) | 19.4 / 5.8 | 9.9 / 3.0 | 9.9 / 3.0 |
| Common Voice 17 id (3629 utts) | 21.1 / 7.7 | 8.9 / 2.9 | 9.0 / 2.8 |
Telephone / Opus / AAC channel + short context (500 CV clips, training-time eval): 10.6 WER.
Latency, whisper.cpp q8_0, 4 s utterance:
| CPU | Settings | ms / utterance | RTF |
|---|---|---|---|
| RK3588, Cortex-A76 x4 (Orange Pi 5 Plus) | taskset -c 4-7, -t 4 -ac 256 | 554 | 0.14 |
| x86 AMD EPYC 7302P | -t 4 -ac 256 | 598 | 0.15 |
| x86 AMD EPYC 7302P | -t 8 -ac 256 | 359 | 0.09 |
| Cortex-A53 x4 (Orange Pi Zero3) | -t 4 -ac 256 | 7200 | 1.8: not realtime, use tiny/base-id |
Output is lowercase without punctuation.
model.safetensors (fp16) + tokenizer/config: transformersggml-small-id-q8_0.bin (264 MB): whisper.cpp. On ARM, q8_0 beats q5_0 on speed.ct2-int8/: CTranslate2 int8_float16 for faster-whisper on GPU (T4: 106 ms per 4 s utterance, single stream). On CPU prefer whisper.cpp: faster-whisper pads every clip to 30 s.bash
# -ac = encoder positions: 50 per second of audio, round up to a multiple of 64 (4 s -> 256, 8 s -> 448)whisper-cli -m ggml-small-id-q8_0.bin -l id -t 4 -ac 256 -bs 1 -bo 1 -nt -f audio16k.wavpython
# GPUfrom huggingface_hub import snapshot_downloadfrom faster_whisper import WhisperModelpath = snapshot_download("maleo-ai/whisper-small-id", allow_patterns="ct2-int8/*")model = WhisperModel(f"{path}/ct2-int8", device="cuda", compute_type="int8_float16")segments, _ = model.transcribe("audio.wav", language="id", beam_size=1, vad_filter=True)print(" ".join(s.text for s in segments))python
from transformers import pipelineasr = pipeline("automatic-speech-recognition", model="maleo-ai/whisper-small-id")print(asr("audio.wav", generate_kwargs={"language": "indonesian", "task": "transcribe"})["text"])bibtex
@misc{irawan2026whispersmallid, author = {Eka Tresna Irawan}, title = {whisper-small-id: Whisper small fine-tuned for Indonesian speech recognition}, year = {2026}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/maleo-ai/whisper-small-id}}}# -ac = encoder positions: 50 per second of audio, round up to a multiple of 64 (4 s -> 256, 8 s -> 448)whisper-cli -m ggml-small-id-q8_0.bin -l id -t 4 -ac 256 -bs 1 -bo 1 -nt -f audio16k.wav# GPUfrom huggingface_hub import snapshot_downloadfrom faster_whisper import WhisperModelpath = snapshot_download("maleo-ai/whisper-small-id", allow_patterns="ct2-int8/*")model = WhisperModel(f"{path}/ct2-int8", device="cuda", compute_type="int8_float16")segments, _ = model.transcribe("audio.wav", language="id", beam_size=1, vad_filter=True)print(" ".join(s.text for s in segments))from transformers import pipelineasr = pipeline("automatic-speech-recognition", model="maleo-ai/whisper-small-id")print(asr("audio.wav", generate_kwargs={"language": "indonesian", "task": "transcribe"})["text"])@misc{irawan2026whispersmallid, author = {Eka Tresna Irawan}, title = {whisper-small-id: Whisper small fine-tuned for Indonesian speech recognition}, year = {2026}, publisher = {Hugging Face}, howpublished = {\url{https://huggingface.co/maleo-ai/whisper-small-id}}}