Whisper large v3
7900°
openai | speech model | Apache-2.0 license | 23.0 GB as a torrent. Speech recognition workhorse. Full mirror of openai/whisper-large-v3 (safetensors + pt + tf + flax). Whisper is a state-of-the-art model for automatic speech recognition (ASR) and speech translation, proposed in the paper Robust Speech Recognition via Large-Scale Weak Supervision by Alec Radford et al. from OpenAI. Trained on >5M hours of labeled data, Whisper demonstrates a strong ability to generalise to many datasets and domains in a zero-shot setting.
Guides for this model
Best local LLM by use case (October 2026): the right open model for every job
What is The Hugging Bay? A mirror index for open models, and how to verify a download with its hashes
Open weights vs open source vs API-only: what you are actually allowed to do
How to Install Ollama and Run a Local AI (Windows, Mac, Linux)
What is a GGUF file? Quantized models explained (Q4, Q8, fp8, NF4)
Captain's notes
Notes from 2026-10-13
Whisper Large v3 is OpenAI's flagship automatic speech recognition and speech translation model, trained on more than five million hours of labeled audio. Its scale gives it strong zero-shot generalization across languages, accents, and domains without fine-tuning. If you need reliable transcription or translation straight out of the box, this is the benchmark most others are measured against.
Known for
- Strong zero-shot generalization across languages, accents, and noisy audio.
- Handles both transcription and speech-to-text translation in one model.
- Trained on over five million hours of labeled data — unusually large for a speech model.
- Available in multiple weight formats: safetensors, PyTorch, TensorFlow, and Flax.
- Apache 2.0 licence — permissive for commercial and research use.
Watch out for
- At 23 GB the model is heavy; plan your hardware accordingly before downloading.
- Open weights are available but the open_weights flag here is marked false — verify the torrent source before use.
Best for
Prompts to try
Transcribe a recorded meeting
I'm attaching an audio file of a one-hour team meeting recorded over a video call. Transcribe it in full, preserving speaker turns where you can identify them, and flag any segments where the audio was unclear.
Translate a foreign-language clip
Attached is a short audio clip of a news broadcast in French. Transcribe the original French and then provide an English translation, keeping the two versions clearly separated.
Transcribe accented technical speech
This audio is a recorded lecture on semiconductor fabrication delivered by a non-native English speaker in a noisy lecture hall. Transcribe it as accurately as you can, preserving technical terminology.
Compare with
- GPT-4o (2024-11-20)API-only model128,000 token context · $2.50/M input, $10.00/M output
- GPT-4oAPI-only model128,000 token context · $2.50/M input, $10.00/M output
- GPT-4o (2024-05-13)API-only model128,000 token context · $5.00/M input, $15.00/M output
- GPT Audio MiniAPI-only model128,000 token context · $0.60/M input, $2.40/M output
More text models from openai
Questions people ask
- Can I run Whisper Large v3 locally?
- Yes — the weights are distributed under Apache 2.0 and the full model (safetensors, PyTorch, TensorFlow, and Flax formats) is available as a 23 GB torrent, so local deployment is straightforward if you have the hardware for it.
- What languages does Whisper Large v3 support?
- Whisper was trained on multilingual audio at scale and handles transcription and translation across a wide range of languages in a zero-shot setting; the maker has not published a definitive language list on this page.
- How does Whisper Large v3 differ from earlier Whisper versions?
- OpenAI has not published a detailed diff on this page, but Large v3 is the current top tier of the Whisper family — the version most benchmarks and integrations now default to when they cite Whisper performance.
Captain's verdictThe default choice for serious speech recognition work: permissive licence, multiple weight formats, and zero-shot breadth that smaller ASR models rarely match.
Captain writes these notes from the model's own description and model card. Prices and context sizes are the provider's at the time of writing and can change.
Ranking badge
Updated Oct 22, 2026
Made this model? Show this badge on your page.
Paste it into your Hugging Face card or Civitai description.
Also ranked: #77 Hottest Text / LLM text model
Not this creator?
Get your own badge
whisper large v3 Popularity Trend
Heat score, last 12 months
Heat score
7,900°
This week
n/a
Wasn't released/tracked
This month
n/a
Wasn't released/tracked
Past year
n/a
Wasn't released/tracked
7,000°
Floor
The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.
+900°
Torrent seeders
1 people keep serving the weights over torrents or hosted mirrors. Serving a file costs real bandwidth and says the weights are still wanted, so each seeder counts as 1,000 downloads in the download term.
Show detailed breakdown
Every number on this site can be checked. This model's heat score is 7,900°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.
- 1Start at the floor.Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.7,000°running total
- 2Add the downloads.1,000 download-equivalents in all, from Torrent seeders. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.+900°7,900°running total
- =The heat score.Where this model stands on every list of this site. Nothing else adjusts it.7,900°
Glossary: the terms used here
- Heat score
- One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
- Floor
- The 7,000° every model with real data starts from. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
- Download-equivalents
- Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
- Log scale
- Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
- Likes
- Thumbs up and likes from every source, worth half a download each on the log scale.
- Adoption rate
- How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
- Measured and estimated
- Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
- Seeder
- Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
- AI Horde
- A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
- Generation sites
- Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
- OpenRouter tokens
- A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
- Full model (checkpoint)
- The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
- LoRA and embedding
- Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
- Family and weights
- The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
- Age
- Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
- Family boost
- A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
- Stand-in score
- A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
- New! (grace period)
- A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
- Trend
- How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
- Typical model
- The middle of the catalog: half the models with a figure grew faster over the period, half slower.
How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.
Run Locally
How to install
Best local LLM by use case (October 2026): the right open model for every job
Oct 13, 2026
Torrents
openai/whisper-large-v3
flax_model.msgpack
pytorch_model.fp32-00001-of-00002.bin
model.fp32-00001-of-00002.safetensors
pytorch_model.bin
model.safetensors
pytorch_model.fp32-00002-of-00002.bin
model.fp32-00002-of-00002.safetensors
Torrents are shared peer to peer by their seeders; ModelTrends.ai hosts no files. Open the magnet link with a BitTorrent client and compare the finished file's checksum with the one on the listing.
Whisper large v3 is a text model for the Text / LLM family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Text / LLM models and check its heat score to see how it is trending.
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153