| Solid work — testing for mobile deployment | 3morixd | open | 0 | disc |
| Add Vaani-Benchmark-V1.0 Hindi WER eval results | PranavdbhatArtpark | open | 0 | disc |
| Update README.md | dingaopaicandu | open | 0 | disc |
| anis | Aniskhan29 | draft | 0 | disc |
| anis | Aniskhan29 | open | 0 | disc |
| Benchmark: FunASR 170x realtime vs Whisper 13x — non-autoregressive alternative | langgz | open | 0 | disc |
| whisper over vllm. 30 seconds transcriptions | jxadro | open | 0 | disc |
| vllm real-time support | jxadro | open | 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 |
| whisper | tom1202 | draft | 0 | disc |
| HF whisper api bug | dziz | open | 0 | disc |
| test-purpose | chrissneakrs | draft | 0 | disc |
| Upload 28 files | Ananthusajeev190 | open | 0 | disc |
| Upload __init__ (1) (1) (1).py | Ananthusajeev190 | open | 0 | disc |
| Jjh | mazenAsaad | open | 0 | disc |
| Whisper-WebUI Premium - Ultra Fast and High Accuracy Speech to Text Transcripton App for All Languages - Windows, RunPod, Massed Compute 1-Click Installers - Supporting RTX 1000 to 5000 series | MonsterMMORPG | open | 0 | disc |
| Upload quran-in-modern-english (1) (1).pdf | alayaei | open | 0 | disc |
| Whisper only transcribes the English words and ignores the rest of the Spanish audio | davera-017 | open | 0 | disc |
| Upload Новая запись 5.m4a | Artem2308 | open | 0 | disc |
| Upload Новая запись 5.m4a | Artem2308 | closed | 0 | disc |
| bot | Dieselcenter | draft | 0 | disc |
| *
Title: Getting 410 Gone error on all Whisper models via Inference API - Are they available on free tier? | EzekielSolutions | open | 0 | disc |
| Request: DOI | MrAaronJR | open | 0 | disc |
| Upload Copy of EveAoif copy.mp3 | deleted | closed | 0 | disc |
| Upload Lilla 1.m4a | deleted | open | 0 | disc |
| Upload RingVideo_20250907_162127_ENHANCED.wav | murdock65 | open | 0 | disc |
| Upload RingVideo_20250907_162127_ENHANCED.wav | murdock65 | open | 0 | disc |
| Upload Flintstones Unheard.mp3 | Xeeeefi | open | 0 | disc |
| Upload 20250821_100154_0757866036.wav | Amani1310 | open | 0 | disc |
| deneme | NNEMES1SS | draft | 0 | disc |
| Code Switching using Whisper-large-v3 | indrasn0wal | open | 0 | disc |
| Upload New Recording 4.m4a | Enwallace | open | 0 | disc |
| Upload Ног.wav | Samo2850 | closed | 0 | disc |
| Can Deepspeed ZeRO3 be used for Sharding with Whisper-large-v3? | PhoenixAxis | open | 0 | disc |
| What language does "jw" in generation_config.json represent? | ts0923 | closed | 0 | disc |
| Fix example usage | bezzam | open | 0 | disc |
| RuntimeError: Trying to backward through the graph a second time | Sarwg | open | 0 | disc |
| 语音模型 | skyhe666 | draft | 0 | disc |
| Incorrect feature_size in preprocessor_config.json (should be 80) | alexg1802 | open | 0 | disc |
| Upload 60fps Audio 2_45.wav | 11fred11 | open | 0 | disc |
| Audio refinning | Baalbatos | draft | 0 | disc |
| BTS | Birima | open | 0 | disc |
| Upload AUDIO.mp3.mp3 | OJG15 | open | 0 | disc |
| Video format problem. | pantorn | open | 0 | disc |
| Word Timestamps error: RuntimeError: The expanded size of the tensor (69) must match the existing size (72) at non-singleton dimension 1. Target sizes: [1, 69]. Tensor sizes: [72] whisper word. | muaviyaijaz123 | open | 0 | disc |
| Muniyan | Orion14 | open | 0 | disc |
| 有趣的對話 | HuskyLi | closed | 0 | disc |
| two warnings | youarecode | open | 0 | disc |
| whisper large v3 finetuning using our own dataset | rifasca | open | 0 | disc |
| Upload New Recording 3.m4a | Hellometo | open | 0 | disc |
| Why does a tiny silence at the start of my audio change Whisper’s transcription? | dylanewbie | open | 0 | disc |
| Upload 10 files | Usshhaa | open | 0 | disc |
| Whisper openai vs hugging face question | Sin2pi | open | 0 | disc |
| what are the limits for Whisper here? | vendeza | open | 0 | disc |
| Rename README.md to README.mdwas könnte die Ursache für Kopf- und Nackenschmerzen Blutdruckschwankungen Papillenödem und übelkeit sein | Oskar000 | open | 0 | disc |
| getting an error trying to extract word-level timestamps | SphinxKing | open | 0 | disc |
| Download error. Manually specifying the catalog with models. | Incrediblecat | open | 0 | disc |
| Can I use a CLI of it? Just found this project, no experience with AI, just want to convert audio speech to text | vitaly-zdanevich | open | 0 | disc |
| Upload AUD-20250217-WA0001.m4a | Gerald02 | open | 0 | disc |
| Extract words with timestamps | codingyash | open | 0 | disc |
| Working example on Mac M-series | pajikos | open | 0 | disc |
| [badcase report] observe significant recognition errors on an example of libri_light dataset. | lawlict | open | 0 | disc |
| Upload audio1477337879.m4a | Elena9292 | open | 0 | disc |
| Multi task finetuning (transcribe and translate) | Phil-AB | open | 0 | disc |
| SegmentAnything Ultra V2 | didi4725 | open | 0 | disc |
| How to freeze layers and fine tuning | Sarwg | open | 0 | disc |
| Challenges in Distinguishing Similar Phonemes (e.g., 'B' and 'V') in License Plate Speech Recognition Using Whisper-Large Model | dylanewbie | open | 0 | disc |
| Update README.md | munmun341 | closed | 0 | disc |
| Inference on fine-tuned whisper-large-v3 is not working, but is working on pre-trained model and whisper-medium | ivabojic | open | 0 | disc |
| 🚩 Report: Not working | ednsinf | open | 0 | disc |
| Speech recognition broken down by speakers | tur0kmag | open | 0 | disc |
| finetuning whisper large on google colab - pro or pro+ which one is best? | andromeda01111 | closed | 0 | disc |
| the chinese training data of the model is contaminated | bookwoods123 | open | 0 | disc |
| Specify language for transcribing with HuggingFace API | mikealexx | open | 0 | disc |
| Isolate search for a single language | edyrkaj | open | 0 | disc |
| Whisper-GUI | PrensCin | open | 0 | disc |
| How to get SRT file as output | dinesh-001 | open | 0 | disc |
| whisper large v3 turbo | deepdml | open | 0 | disc |
| Missing spaces between chunks in longform fine tune outputs & importance of tokenizer.json | saj-bot | open | 0 | disc |
| Update README.md | Ironajijiul11 | open | 0 | disc |
| What is the accuracy of the model? Why can't I fine-tune when I set the accuracy to FP16? | chengligen | open | 0 | disc |
| Help for absolute AI beginners | TobiasKuch | open | 0 | disc |
| Single word transcription for a audio file with ~1.5m frames | KevalRx | open | 0 | disc |
| Where can I find all model-specific parameters that can be passed to this model in the from_pretrained method? | denis-kazakov | closed | 0 | disc |
| how to get n-best list generated by Whisper. | deleted | open | 0 | disc |
| Hugging Face Model Deployment and Library Dependency Issues | NeuraFusionAI | open | 0 | disc |
| Issue - Internal Server Error (Serverless API) | tushar310 | open | 0 | disc |
| how many GPU memory do I need to finetune largeV3 | lanejohn | open | 0 | disc |
| Better output in INT8 | aney | open | 0 | disc |
| Index # is out of bounds for dimension 0 with size # Error | mh1000 | closed | 0 | disc |
| index # is out of bounds for dimension 0 with size # | nehahumbe | closed | 0 | disc |
| how to translate model ( whisper-small ) to pt file (small.pt)? | lihenan1996 | open | 0 | disc |
| how to get the same output result format from the pipeline as we get from the open ai whisper? | aheed911 | open | 0 | disc |
| Update README.md | sanchit-gandhi | merged | 0 | disc |
| 🚩 Report | dinlun777 | open | 0 | disc |
| الأصدقاء | monir2006 | open | 0 | disc |
| Add Urdu (Pakistan) language speech to text detection | AamirFarooq | open | 0 | disc |
| How to achieve known text content and obtain the timestamp of the text corresponding to the audio | RichardQin | closed | 0 | disc |
| issue | rkvisio | closed | 0 | disc |
| whisper segments | world-of-ai | open | 0 | disc |
| Git repository or how to instructions on downloading and using the model | J-PROGRAMMER | open | 0 | disc |
| Rename README.md to wangdaoqi | dqoqi | open | 0 | disc |
| Hyperparams optimization with LoRA on Whisper | luigimontaleone | open | 0 | disc |
| Rename README.md to Quaranthuit | Etaduri | open | 0 | disc |
| Update README.md | MMXXMM | open | 0 | disc |
| Is it possible to set/output segments as in Open AI's API? For example avg_threshold,temperature,compression_ratio. | rodosabbath | open | 0 | disc |
| list index out of range with word level timestamps | mkvbn | open | 0 | disc |
| errors when running whisper locally | luigimontaleone | closed | 0 | disc |
| YOU ARE HYPOCRITES! | jawad1347 | open | 0 | disc |
| Set temperature and prompt possible? | jeffuli755 | open | 0 | disc |
| FP16 vs FP32 | Taylor658 | closed | 0 | disc |
| Update README.md | reach-vb | merged | 0 | disc |
| Issue when trying to run Whisper offline from locally saved pretrained model | georgis-agent | open | 0 | disc |
| Best strategy for inference on multiple GPUs | symdec | open | 0 | disc |
| "Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained." | dwiraamadhan | open | 0 | disc |
| Issue with inference endpoints | simon5454 | open | 0 | disc |
| Create 1 | ring23 | open | 0 | disc |
| Update README.md | KashaSasha | open | 0 | disc |
| Upload 28 May, 15.58_.aac | lenaelena | open | 0 | disc |
| Browse to upload file results in same default file, cannot upload audio file on demo page | BladedSupernova | open | 0 | disc |
| Update README.md | ochoseistres | open | 0 | disc |
| KeyError: 'whisper' | aiyaqingzheng | open | 0 | disc |
| The meaning of some special token fields | tlain | open | 0 | disc |
| how to transcribe hundreds of local audio files once? | myspace-ai | open | 0 | disc |
| Error: ffmpeg was not found but is required to load audio files from filename | Vladmir1235432 | open | 0 | disc |
| Only 30 second of my audio get transcripted | Ganz00 | closed | 0 | disc |
| Improving reliability, using prompt parameter | dcd12345678 | open | 0 | disc |
| None | Pytagora | open | 0 | disc |
| supress the number in whisper model | saichand09 | open | 0 | disc |
| Whisper Tokenizer bos_token maybe wrong | moncefbenaicha | closed | 0 | disc |
| Update README.md | Reed23 | closed | 0 | disc |
| Upload Jens Wörle Onyo.m4a | lennartuh | open | 0 | disc |
| Meaningless or repetitive sentences continue to be generated. | kbuwel | open | 0 | disc |
| Audio input consists of only 3000. Short-form transcription is activated.no_speech_threshold is set to 0.5, but will be ignored. | rizwanishaq | open | 0 | disc |
| transcribing chinese audio with the this model, the output text lacks punctuation | TaoGoblin | open | 0 | disc |
| Issues with transcription of Burmese audio | hanshupe | open | 0 | disc |
| How can i return both word level and segment together when using hugging face transformer? | lilijy | open | 0 | disc |
| Incoherences in timestamps between chunked and sequential form | vprosadm | open | 0 | disc |
| How we can use this model to achieve a real-time trans？ | Von-violet | open | 0 | disc |
| How to get accuracy of transcription from the model? | Atulad | open | 0 | disc |
| Module not found error. No module named GTTS. | BeyondStreamlit | open | 0 | disc |
| Enhancing Pipeline with Speech Probability for Reduced Hallucination | rizwanishaq | open | 0 | disc |
| Rename README.md to persian | Zabs | open | 0 | disc |
| OpenAI Whisper Support Urdu (Pakistan) language? | AamirFarooq | open | 0 | disc |
| How to mention lanuage parameter on inference api | aitransync | open | 0 | disc |
| Download and Load model on local system. | RebelloAlbina | open | 0 | disc |
| How to save the loss value for each step during the training process? | zhouwen999 | open | 0 | disc |
| Update README.md | BWSTUDIO | closed | 0 | disc |
| Auto speech/languages detection in Real Time streaming? | sabys | open | 0 | disc |
| not transcribing to english | aitransync | open | 0 | disc |
| Does it support Korean translation and speech? :) | JinPark | open | 0 | disc |
| Transcript an Spanish audio | Andrews99 | open | 0 | disc |
| is it possible to access the transcript result in batches after each chunk has finished? | hanifanggawi | open | 0 | disc |
| how to download model and load model and use it | r5avindra | open | 0 | disc |
| [AUTOMATED] Model Memory Requirements | model-sizer-bot | open | 0 | disc |
| Output Discrepancy | eBisw | open | 0 | disc |
| Transcription and Translation In the same call | saalnlp | open | 0 | disc |
| Create handler.py | gehrketech | closed | 0 | disc |
| Update forced decoder ids | sanchit-gandhi | merged | 0 | disc |
| model in closed network | iamwhoiamm | open | 0 | disc |
| Trouble shooting local inference on whisper | RESOLVER101757 | open | 0 | disc |
| The new Longform transcription method | deep-intel | open | 0 | disc |
| Make sure language detection is trigger by default | patrickvonplaten | merged | 0 | disc |
| Upload vocab.json | smerchi | open | 0 | disc |
| How to adapt for low resource language? | Imran1 | open | 0 | disc |
| Problems with AutoProcessor | Kwang442 | open | 0 | disc |
| Suddenly all my transcriptions are in English | WWCF | open | 0 | disc |
| A simple question, may I ask you all | yebing | closed | 0 | disc |
| Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. | patrickvonplaten | merged | 0 | disc |
| Correct long-form generation config parameters 'max_initial_timestamp_index' and 'prev_sot_token_id'. | patrickvonplaten | closed | 0 | disc |
| Transcription in different languages for Punjabi audio | jssaluja | open | 0 | disc |
| I want to use Whisper on a piece of hardware | Avinier | open | 0 | disc |
| How to fix "TypeError: expected str, bytes or os.PathLike object, not NoneType" when specifying the local whisper model | BenjaminChu | open | 0 | disc |
| Speaker Embedding | bertrand-fournel | open | 0 | disc |
| Flash Attention 2.0 does not work. | KSDFOSSDGHJ | closed | 0 | disc |
| whisper jax diarization Icelandic | Dondada79 | open | 0 | disc |
| Translating English Audio Into Spanish Text | stvnchnsn | open | 0 | disc |
| Error with word level timestamps - ValueError: set return_segments=True | dkincaid | open | 0 | disc |
| Passing parameters to the model deployed on HF Inference Endpoints | dkincaid | open | 0 | disc |
| Does whisper-large-v3 work on Sagemaker? | dkincaid | open | 0 | disc |
| Which File Shall I Download from The Files and Versions | BenjaminChu | open | 0 | disc |
| Transcribing multiple languages in single audio file | supercharge19 | open | 0 | disc |
| Is there any way we can get no_speech_probability from the pipeline? | rizwanishaq | open | 0 | disc |
| how to handle input audio files with either white noise or general noise and no speech | unk1911 | open | 0 | disc |
| changed use_flash_attention_2=True to attn_implementation="flash_attention_2" | macadeliccc | open | 0 | disc |
| Whisper parameters? | Megatron17 | open | 0 | disc |
| Whisper large v3 can not recognize speech after Fine-Tune | bardenthenry | open | 0 | disc |
| how download large version? | Timnorth | open | 0 | disc |
| Crashed: when getting end of sentence timestamps and word-level timestamps at the same time | liutian-sunshine | closed | 0 | disc |
| I've noticed that Uyghur language is not available. Is it possible to add the Uyghur (ug) dataset from the Mozilla Foundation's Common Voice 13.0 for training? | almjanx | open | 0 | disc |
| is parallel processing possible with DLC Deployement? | SharatChandra | open | 0 | disc |
| Error: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED | duzm | open | 0 | disc |
| config1.json | stasluzan | closed | 0 | disc |
| Update README.md | Mucahit01 | open | 0 | disc |
| Training for translation | tirtohadi | open | 0 | disc |
| Whisper-Large-V3 does not work with explicit use of dtype which is given in config.json | ait-paca | open | 0 | disc |
| Update README.md | joey1895 | open | 0 | disc |
| What azure compute instance will work? | Jayantabasumatary1 | open | 0 | disc |
| Getting pipeline time estimate | wwilcz | open | 0 | disc |