GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
burkialisher5
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
burkialisher5
Model Tree
Input Modalities
Output Modalities
Supported Functionality
pashto-ghag-whisper-medium-asr)oru)WhisperForConditionalGeneration (Whisper Medium - 769M parameters)r=32, alpha=64, modules: q_proj, v_proj, k_proj, out_proj, fc1, fc2)| Model Version | Target Language | WER (%) | CER (%) | Delta WER vs Baseline |
|---|---|---|---|---|
| Zero-Shot Pashto Ghag Base | Ormuri (oru) | 84.86% | 37.08% | Baseline |
| Fine-Tuned Checkpoint 100 | Ormuri (oru) | 36.54% | 12.89% | -48.32 pp |
| Fine-Tuned Checkpoint 200 | Ormuri () |
python
import torchfrom transformers import pipeline# Initialize pipelineasr_pipeline = pipeline("automatic-speech-recognition",model="burkialisher5/Ormuri_ASR",device="cuda" if torch.cuda.is_available() else "cpu",torch_dtype=torch.float16 if torch.cuda.is_available() else torch.float32,)# Transcribe Ormuri audio fileresult = asr_pipeline("path/to/ormuri_sample.wav")print("Ormuri Transcription:", result["text"])
python
import torchimport librosafrom transformers import WhisperProcessor, WhisperForConditionalGenerationdevice = "cuda" if torch.cuda.is_available() else "cpu"processor = WhisperProcessor.from_pretrained("burkialisher5/Ormuri_ASR")model = WhisperForConditionalGeneration.from_pretrained("burkialisher5/Ormuri_ASR",torch_dtype=torch.float16 if device == "cuda" else torch.float32).to(device)# Load audio resampled to 16kHzaudio, sr = librosa.load("path/to/ormuri_sample.wav", sr=16000)input_features = processor(audio, sampling_rate=16000, return_tensors="pt").input_features.to(device)if device == "cuda":input_features = input_features.to(torch.float16)forced_decoder_ids = processor.get_decoder_prompt_ids(language="pashto", task="transcribe")with torch.no_grad():predicted_ids = model.generate(input_features, forced_decoder_ids=forced_decoder_ids, max_new_tokens=225)transcription = processor.batch_decode(predicted_ids, skip_special_tokens=True)[0]print("Ormuri Transcription:", transcription)
lr=3e-4).pashto-ghag-whisper-medium-asr).oru| 25.78% |
| 8.35% |
| -59.08 pp |
| Fine-Tuned Checkpoint 300 | Ormuri (oru) | 23.18% | 7.29% | -61.68 pp |
| Fine-Tuned Checkpoint 400 | Ormuri (oru) | 20.44% | 6.41% | -64.42 pp |
| Fine-Tuned Checkpoint 600 (This Model) | Ormuri (oru) | 18.39% | 5.65% | -66.47 pp (Best) |