| Upload hqdefault.jpg | Derand | open | 0 | disc |
| Interesting work — mobile AI perspective | 3morixd | open | 0 | disc |
| Even faster alternative: FunASR SenseVoice (170x realtime, CPU-friendly) | langgz | open | 0 | disc |
| Request: DOI | mohhaamed | closed | 0 | disc |
| Whisper Web UI Ultimate Published With So Many Features - 1-Click to Install Windows, RunPod, Massed Compute, Linux, CUDA 13, Torch 2.9.1 with pre-compiled wheels | MonsterMMORPG | open | 0 | disc |
| Add Open ASR Leaderboard evaluation results | SaylorTwift | open | 0 | disc |
| None | Kwan0 | closed | 0 | disc |
| whisper-large-v3-turbo Hugging Face API bug | dziz | open | 0 | disc |
| test | yasharhabibzadeh | draft | 0 | disc |
| Vllm | elstoneng | open | 0 | disc |
| The model is now added to WebAI.js. Run it in your browser with no code required. | AxolsWebAI | open | 0 | disc |
| Example doesn work because of "ValueError: You have passed more than 3000 mel input features (> 30 seconds) " | pengzhenghao97 | open | 0 | disc |
| Whisper and the ethics of listening at scale | elly99 | open | 0 | disc |
| Update README.md | DeOSAlphaHI | closed | 0 | disc |
| ImportError: cannot import name 'DataCollatorSpeechSeq2SeqWithPadding' from 'transformers' | SudheenK | open | 0 | disc |
| Fix example usage | bezzam | open | 0 | disc |
| Fix example usage | bezzam | closed | 0 | disc |
| Inference on AWS INF 2 | VasuML | open | 0 | disc |
| translate not working | devs9 | open | 0 | disc |
| Potential Inconsistencies Between Model and Base model License | yueyangchen | open | 0 | disc |
| how can I configue the generation of whisper-large-v3-turbo only for "zh"? | Fan0718 | open | 0 | disc |
| WTF is going on? | vbarrier | open | 0 | disc |
| Whisper-large-v3 finetuning using our own dataset | rifasca | open | 0 | disc |
| Inference API error with Whisper, return_timestamps parameter | oslv | open | 0 | disc |
| Update README.md | tefamcse | open | 0 | disc |
| Upload l ۲ با | Hhhuu | closed | 0 | disc |
| Upload Khun Rishi - 3.4.25.m4a | Pongsa5 | open | 0 | disc |
| Update README.md | jmshd | closed | 0 | disc |
| Model incapabilities in Turkish | afsharbey | open | 0 | disc |
| How can I use the model for translation from English to French? | inuwamobarak | open | 0 | disc |
| Upload Новая запись 6-enhanced-v2.wav | gazzati | open | 0 | disc |
| pricing about Inference for openai/whisper-large-v3-turbo | Nagsrujan | open | 0 | disc |
| AWS Bedrock model id not working boto3 | nahuelramos | open | 0 | disc |
| Bug: Timestamps reset every 30 seconds with return_timestamps=True | fortytwoprod | open | 0 | disc |
| Error exporting whisper-large-v3-turbo to onnx with optimum | rayli1107 | open | 0 | disc |
| Upload Sungrow meeting.m4a | DimitrisK75 | open | 0 | disc |
| ASR output getting clipped after fine-tuning | saana25 | open | 0 | disc |
| Update README.md | Pedropomex | open | 0 | disc |
| Request: DOI | Banick | open | 0 | disc |
| Unable to recognize the lyrics | sherlockya | open | 0 | disc |
| Having a timestamp problem while trying to make a .srt file from the audio of a video | muratowski | open | 0 | disc |
| condition_on_prev_tokens doesn't work! | skycyou | open | 0 | disc |
| Me gusta la pija | Gabipalanza | open | 0 | disc |
| Upload ChatGPT.m4a | jschust1 | closed | 0 | disc |
| projet | khalid0s | closed | 0 | disc |
| How do I return timestamps on inference serverless api??? | tshroveOntelio | open | 0 | disc |
| Reading | BN1206 | open | 0 | disc |
| how to set the "initial_prompt"? | bookwoods123 | open | 0 | disc |
| 🚩 Report: Not working | ednsinf | open | 0 | disc |
| Translation task | JulienNawak | open | 0 | disc |
| Upload R-U1).m4a | Batea | open | 0 | disc |
| woops. My typo | musickiller | closed | 0 | disc |
| Benchmarks against distil-whisper/distil-large-v3? | datasaurus | open | 0 | disc |
| Use model ID instead of local tmp path in config | mhconradt | open | 0 | disc |
| AWS Sagemaker Inference Endpoint Error : unsupported operand type(s) for *: 'NoneType' and 'Tensor' | deepanshgupta-xpanse | open | 0 | disc |
| How can I deploy this model whisper-large-v3-turbo on my EC2 CPU instance? | Rushikesh7766 | open | 0 | disc |
| Interview request: Thoughts on genAI evaluation & documentation | evatang | open | 0 | disc |
| the chinese training data of the model is contaminated | bookwoods123 | open | 0 | disc |
| Why continue the charade? to get people to stay on the platform? | Sin2pi | closed | 0 | disc |
| yyhh | zeous | open | 0 | disc |
| 操作方法 | simple0 | open | 0 | disc |
| When using sliding window, the timestamps are not displayed correctly | WJO | open | 0 | disc |
| Upload 2013 - Mémento de pisciculture d'étang - Schlumberger, Girard-extrait zooplancton_041000.pdf | apdradinaamicc | open | 0 | disc |
| Can I give prompt to the Whisper turbo model as I could give to the previous models? | ashish3150 | open | 0 | disc |
| How long can it translate? | JUNGU | open | 0 | disc |
| TRY | GKBABY | draft | 0 | disc |
| Any efficient way to do diarization while keeping this model accuracy at transcribing multi-language audio? | raresmose | closed | 0 | disc |
| When translating Chinese audio, there are no punctuation marks in the output | thehonestbob | open | 0 | disc |
| Make Model Name Consistent with other Whisper Models | WillHeld | open | 0 | disc |
| Extremely slow, feel like running large-v2 | ThanhHuyLe | open | 0 | disc |
| Solved | ustcmyw | closed | 0 | disc |
| Just for inference? | Sin2pi | open | 0 | disc |
| float32 weight pretty please! | ctranslate2-4you | closed | 0 | disc |
| Update README.md | reach-vb | merged | 0 | disc |
| IndexError: list index out of range. How to solve? | seb19986 | open | 0 | disc |
| Add correct library tag | osanseviero | open | 0 | disc |
| Too slow | Xis | open | 0 | disc |
| Model binary | svtxvt | open | 0 | disc |
| PEFT inquiry | MightyStudent | open | 0 | disc |
| Fine-tuning Whisper Turbo for Arabic: Expected Accuracy Improvements? | neethuvm | open | 0 | disc |
| Torch compile + dynamo error | ParadiseN | open | 0 | disc |
| Error: chunk_length_s | seb19986 | open | 0 | disc |
| RuntimeError: "reflection_pad2d" not implemented for 'Half' | seb19986 | open | 0 | disc |
| Better train whisper large V3 or whisper turbo ? | GALEON-AI | open | 0 | disc |
| Which infra to run openai/whisper-large-v3-turbo ? | Jack0o | open | 0 | disc |
| please post an mlx version or example. IS there any change to deploy on the M series chip? | KeTuTu | closed | 0 | disc |
| Replicate Demo | chenxwh | open | 0 | disc |
| Update README.md | reach-vb | merged | 0 | disc |
| cuanta gpu necesito para ejecutarlo ? | alfanumericbeta | open | 0 | disc |
| colab version or example | Inforline | open | 0 | disc |
| Create tokenizer.json | Jilt | merged | 0 | disc |