GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
selimc
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
selimc
Model Tree
openai/whisper-large-v3-turbo
Input Modalities
Output Modalities
Supported Functionality
This model can be used in various application areas, including
python
import torchfrom transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline device = "cuda:0" if torch.cuda.is_available() else "cpu"torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32 model_id = "selimc/whisper-large-v3-turbo-turkish" 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( "automatic-speech-recognition", model=model, tokenizer=processor.tokenizer, feature_extractor=processor.feature_extractor, chunk_length_s=30, batch_size=16, return_timestamps=True, torch_dtype=torch_dtype, device=device,) result = pipe("test.mp3")print(result["text"])Due to colab GPU constraints I was able to train using only the 25% of the Turkish data available in the Common Voice 17.0 dataset. 😔
Got a GPU to spare? Let's collaborate and take this model to the next level! 🚀
The following hyperparameters were used during training:
| Training Loss | Epoch | Step | Validation Loss | Wer |
|---|---|---|---|---|
| 0.1223 | 1.6 | 1000 | 0.3187 | 24.4415 |
| 0.0501 | 3.2 | 2000 | 0.3123 | 20.9720 |
| 0.0226 | 4.8 | 3000 | 0.3010 | 19.6183 |
| 0.001 | 6.4 | 4000 | 0.3123 | 18.9229 |
import torchfrom transformers import AutoModelForSpeechSeq2Seq, AutoProcessor, pipeline device = "cuda:0" if torch.cuda.is_available() else "cpu"torch_dtype = torch.float16 if torch.cuda.is_available() else torch.float32 model_id = "selimc/whisper-large-v3-turbo-turkish" 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( "automatic-speech-recognition", model=model, tokenizer=processor.tokenizer, feature_extractor=processor.feature_extractor, chunk_length_s=30, batch_size=16, return_timestamps=True, torch_dtype=torch_dtype, device=device,) result = pipe("test.mp3")print(result["text"])