Whisper · speech to text

Whisper medium

OpenAI's README lists 769 M for this size. The exact count, 763,857,920, is Computed: I added up the tensor shapes in the official model.safetensors header on 19 Nov 2026.

MIT, per OpenAI · Multilingual · Can translate into English

OpenAI's GitHub README says the code and model weights are released under MIT. The Hugging Face repo metadata says apache-2.0 for every size except large-v3-turbo (mit). I follow the GitHub statement and flag the mismatch.

What it is

Whisper writes down speech. It is not a chat model, so this page has no context length and no KV memory math. OpenAI’s name for this file is medium. The README lists 769 M parameters. The exact count, 763,857,920, is Computed from the official safetensors header on 19 Nov 2026.

99 language codes (Computed: tokenizer.py lists 100, and Cantonese only arrived with large-v3). OpenAI's card says strong results in about 10 languages.

From the model card

Strengths

  • OpenAI suggests medium or large for translating into English.
  • Aiko uses it on iPhones with enough memory.

Weaknesses

  • Not in Argmax's iPhone list. Better on a Mac or PC.

File size and memory

These are not the Frankenstein run. Each row keeps the label it came with.

FigureValueLabel
OpenAI 'Required VRAM' (openai-whisper, PyTorch)~5 GBVendor-reported Source
OpenAI relative speed vs large (A100, English)~2xVendor-reported Source
Hugging Face model.safetensors (float32)3.06 GB (3,055,544,304 bytes)Vendor-reported Source
FP16 weights (params x 2 bytes)1.42 GiBComputed params from the safetensors header
whisper.cpp ggml file1.5 GiBVendor-reported Source
whisper.cpp runtime memory~2.1 GBVendor-reported Source

Speed

Whisper medium. Measured on Frankenstein (HP ProLiant DL380p Gen8), 19 Nov 2026. Median of 2 runs. Speed is audio length divided by wall time. Measured
ModelAudioFile on diskWall timeAudio ÷ wallEncoderPeak RSSJFK word errors
mediumJFK sample, 11.0 s1,463 MiB8.93 s1.23×4.36 s2,068 MiB0.0% (0/22 words)
mediumLibriVox Gettysburg Address, 161.2 s1,463 MiB60.64 s2.66×25.28 s2,171 MiB—

Method, commit, and the exact command: methodology.

Measured on Frankenstein (HP ProLiant DL380p Gen8), 19 Nov 2026. A phone speed is not in this run. The Tesla P40 was not used.

Where it runs

Vendor-reported Not listed for any iPhone chip. This is Argmax’s list for WhisperKit, not a test I ran, and it names chips rather than phone models. See Run Whisper on your iPhone and Run Whisper on your computer.

Official downloads

These go to OpenAI or to the whisper.cpp GGML files. They are not store links.

Sources: openai/whisper README (model table) · openai/whisper model card · openai/whisper-medium model card · whisper.cpp models list (ggml file sizes) · WhisperKit device support (Argmax config.json)