Whisper
OpenAIdevelopers.openai.com/api/docs/models/whisper-1
General-purpose speech recognition model
Updated 26 min ago · first seen 11 Sept 2026
model_01M293VC72CHCTNJ08P4S29BGR
- Parameters
- 1.54B
- T2 · 3 h ago
- Released
- 7 Nov 2023
- T2 · 2 h ago
- License
- apache-2.0
- T2 · 2 h ago
Specification
- Release date
- 7 Nov 2023
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Status
- deprecated
Source:OpenAI Platform docsT1observed 3 h agohigh
- Openness
- proprietary
Source:OpenAI Platform docsT1observed 3 h agohigh
- License
- apache-2.0
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Architecture
- WhisperForConditionalGeneration
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Parameters
- 1.54B
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Languages
- en, zh, de, es, ru, ko, fr, ja, pt, tr, pl, ca, nl, ar, sv, it, id, hi, fi, vi, he, uk, el, ms, cs, ro, da, hu, ta, no, th, ur, hr, bg, lt, la, mi, ml, cy, sk, te, fa, lv, bn, sr, az, sl, kn, et, mk, br, eu, is, hy, ne, mn, bs, kk, sq, sw, gl, mr, pa, si, km, sn, yo, so, af, oc, ka, be, tg, sd, gu, am, yi, lo, uz, fo, ht, ps, tk, nn, mt, sa, lb, my, bo, tl, mg, as, tt, haw, ln, ha, ba, jw, su
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 26 min agomedium
- API model id
- whisper-1
Source:OpenAI Platform docsT1observed 3 h agohigh
- File size
- 3.1 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Deprecation date
- 26 Aug 2026
Source:OpenAI Platform docsT1observed 3 h agohigh
- Retirement date
- 26 Feb 2027
Source:OpenAI Platform docsT1observed 3 h agohigh
- Retirement tentative
- No
Source:OpenAI Platform docsT1observed 3 h agohigh
- Hugging Face repo
- openai/whisper-large-v3
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Pipeline tag
- automatic-speech-recognition
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Official page
Source:OpenAI Platform docsT1observed 3 h agohigh
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Downloads
- 5,008,122
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 26 min agomedium
- Likes
- 6,263
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 26 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Groq model id
- whisper-large-v3
Source:Groq — docs & pricingT1observed 3 h agohigh
- Groq pricing note
- $0.111 per hour
Source:Groq — docs & pricingT1observed 3 h agohigh
- Hf inference providers
- deepinfra, fal-ai, hf-inference, replicate, together
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Last modified
- 2024-08-12T10:20:10+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 3 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Downloads all time
- 145,806,497
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 26 min agomedium
- Model type
- whisper
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Tags
- transformers, pytorch, jax, safetensors, whisper, automatic-speech-recognition, audio, hf-asr-leaderboard, en, zh, de, es, ru, ko, fr, ja, pt, tr, pl, ca, nl, ar, sv, it, id, hi, fi, vi, he, uk
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Weights dtype
- F16
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
Each value shows its source, tier and observation time. Conflicting claims are kept side by side and flagged — never averaged. How AI Atlas records facts →
Provenance
Attributed facts
29
Source tiers
T1T210 / 19
Freshest observation
26 min ago
Conflicts
6 flagged
Modalities
Modalities unavailable.
Capabilities
Tool calling
Unavailable
Structured output
Unavailable
Reasoning
Unavailable
Vision
Unavailable
Audio
Unavailable
Fine-tuning available
Unavailable
No capability flags have been observed from a source yet — we do not infer them.
- Languages
- en, zh, de, es, ru, ko, fr, ja, pt, tr, pl, ca, nl, ar, sv, it, id, hi, fi, vi, he, uk, el, ms, cs, ro, da, hu, ta, no, th, ur, hr, bg, lt, la, mi, ml, cy, sk, te, fa, lv, bn, sr, az, sl, kn, et, mk, br, eu, is, hy, ne, mn, bs, kk, sq, sw, gl, mr, pa, si, km, sn, yo, so, af, oc, ka, be, tg, sd, gu, am, yi, lo, uz, fo, ht, ps, tk, nn, mt, sa, lb, my, bo, tl, mg, as, tt, haw, ln, ha, ba, jw, su
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 26 min agomedium
No benchmark results recorded
Current prices
No current prices recorded
Available through 1
Price history
Memory need = bytes per parameter (4-bit ≈ 0.5 × 1.15 overhead, 8-bit 1.0, fp16 2.0) + a KV-cache allowance. Not a measurement.
| Hardware | Quantization | Memory | Est. need | Fits |
|---|---|---|---|---|
| NVIDIA DGX B200 | 4bit | 1,440 GB | 1.4 GB | Yes |
| Apple M3 Ultra | 4bit | — | 1.4 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 1.4 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 1.4 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 1.4 GB | Yes |
| Apple M2 Ultra | 4bit | — | 1.4 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 1.4 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 1.4 GB | Yes |
| NVIDIA H200 NVL | 4bit | 141 GB | 1.4 GB | Yes |
| Apple M1 Ultra | 4bit | — | 1.4 GB | Yes |
| Apple M3 Max | 4bit | — | 1.4 GB | Yes |
| Apple M4 Max | 4bit | — | 1.4 GB | Yes |
| Mac Studio (Apple M5 Max) | 4bit | — | 1.4 GB | Yes |
| MacBook Pro (Apple M5 Max) | 4bit | — | 1.4 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 1.4 GB | Yes |
| Apple M2 Max | 4bit | — | 1.4 GB | Yes |
| NVIDIA H100 NVL | 4bit | 94 GB | 1.4 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 1.4 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 1.4 GB | Yes |
| Apple M1 Max | 4bit | — | 1.4 GB | Yes |
| Apple M4 Pro | 4bit | — | 1.4 GB | Yes |
| Mac mini (Apple M5 Pro) | 4bit | — | 1.4 GB | Yes |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 1.4 GB | Yes |
| Apple M3 Pro | 4bit | — | 1.4 GB | Yes |
| Apple M1 Pro | 4bit | — | 1.4 GB | Yes |
| Apple M2 Pro | 4bit | — | 1.4 GB | Yes |
| Apple M4 | 4bit | — | 1.4 GB | Yes |
| iMac (Apple M4) | 4bit | — | 1.4 GB | Yes |
| Mac mini (Apple M6) | 4bit | — | 1.4 GB | Yes |
| MacBook Air (Apple M5) | 4bit | — | 1.4 GB | Yes |
| MacBook Pro (Apple M5) | 4bit | — | 1.4 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 1.4 GB | Yes |
| Apple M2 | 4bit | — | 1.4 GB | Yes |
| Apple M3 | 4bit | — | 1.4 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 1.4 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 1.4 GB | Yes |
| Apple M1 | 4bit | — | 1.4 GB | Yes |
Ancestors 0
None recorded.
This model
Whisper
1.54B params
Quantizations 0
None recorded.
Descendants 1
- Whisper Large V3 Turbo808.9M
Papers 1
- arXiv:2212.04356Active35
Repositories 0
No repositories linked yet.
As of
Rewind the record: see this entity's attributes exactly as AI Atlas knew them on a given day.
Claim history · Languages
Languageslanguages3
| Value | Valid from → to | Status | Source | Confidence | Extractor |
|---|---|---|---|---|---|
| en, zh, de, es, ru, ko, fr, ja, pt, tr, pl, ca, nl, ar, sv, it, id, hi, fi, vi, he, uk, el, ms, cs, ro, da, hu, ta, no, th, ur, hr, bg, lt, la, mi, ml, cy, sk, te, fa, lv, bn, sr, az, sl, kn, et, mk, br, eu, is, hy, ne, mn, bs, kk, sq, sw, gl, mr, pa, si, km, sn, yo, so, af, oc, ka, be, tg, sd, gu, am, yi, lo, uz, fo, ht, ps, tk, nn, mt, sa, lb, my, bo, tl, mg, as, tt, haw, ln, ha, ba, jw, su | → current | current | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
| en, zh, de, es, ru, ko, fr, ja, pt, tr, pl, ca, nl, ar, sv, it, id, hi, fi, vi, he, uk, el, ms, cs, ro, da, hu, ta, False, th, ur, hr, bg, lt, la, mi, ml, cy, sk, te, fa, lv, bn, sr, az, sl, kn, et, mk, br, eu, is, hy, ne, mn, bs, kk, sq, sw, gl, mr, pa, si, km, sn, yo, so, af, oc, ka, be, tg, sd, gu, am, yi, lo, uz, fo, ht, ps, tk, nn, mt, sa, lb, my, bo, tl, mg, as, tt, haw, ln, ha, ba, jw, su | → | superseded | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
| en, zh, de, es, ru, ko, fr, ja, pt, tr, pl, ca, nl, ar, sv, it, id, hi, fi, vi, he, uk, el, ms, cs, ro, da, hu, ta, no, th, ur, hr, bg, lt, la, mi, ml, cy, sk, te, fa, lv, bn, sr, az, sl, kn, et, mk, br, eu, is, hy, ne, mn, bs, kk, sq, sw, gl, mr, pa, si, km, sn, yo, so, af, oc, ka, be, tg, sd, gu, am, yi, lo, uz, fo, ht, ps, tk, nn, mt, sa, lb, my, bo, tl, mg, as, tt, haw, ln, ha, ba, jw, su | → | superseded | Hugging Face Hub (public pages, model cards, papers)T2 | medium | deterministic |
Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →
Whisper: languages changed from ["en", "zh", "de", "es", "ru", "ko", "fr", "ja", "pt", "t… to ["en", "zh", "de", "es", "ru", "ko", "fr", "ja", "pt", "t…
Languagesen, zh, de, es, ru, ko, fr, ja, pt, tr, pl, ca, nl, ar, sv, it, id, hi, fi, vi, he, uk, el, ms, cs, ro, da, hu, ta, False, th, ur, hr, bg, lt, la, mi, ml, cy, sk, te, fa, lv, bn, sr, az, sl, kn, et, mk, br, eu, is, hy, ne, mn, bs, kk, sq, sw, gl, mr, pa, si, km, sn, yo, so, af, oc, ka, be, tg, sd, gu, am, yi, lo, uz, fo, ht, ps, tk, nn, mt, sa, lb, my, bo, tl, mg, as, tt, haw, ln, ha, ba, jw, su→en, zh, de, es, ru, ko, fr, ja, pt, tr, pl, ca, nl, ar, sv, it, id, hi, fi, vi, he, uk, el, ms, cs, ro, da, hu, ta, no, th, ur, hr, bg, lt, la, mi, ml, cy, sk, te, fa, lv, bn, sr, az, sl, kn, et, mk, br, eu, is, hy, ne, mn, bs, kk, sq, sw, gl, mr, pa, si, km, sn, yo, so, af, oc, ka, be, tg, sd, gu, am, yi, lo, uz, fo, ht, ps, tk, nn, mt, sa, lb, my, bo, tl, mg, as, tt, haw, ln, ha, ba, jw, suhuggingfaceWhisper: languages changed from ["en", "zh", "de", "es", "ru", "ko", "fr", "ja", "pt", "t… to ["en", "zh", "de", "es", "ru", "ko", "fr", "ja", "pt", "t…
Languagesen, zh, de, es, ru, ko, fr, ja, pt, tr, pl, ca, nl, ar, sv, it, id, hi, fi, vi, he, uk, el, ms, cs, ro, da, hu, ta, no, th, ur, hr, bg, lt, la, mi, ml, cy, sk, te, fa, lv, bn, sr, az, sl, kn, et, mk, br, eu, is, hy, ne, mn, bs, kk, sq, sw, gl, mr, pa, si, km, sn, yo, so, af, oc, ka, be, tg, sd, gu, am, yi, lo, uz, fo, ht, ps, tk, nn, mt, sa, lb, my, bo, tl, mg, as, tt, haw, ln, ha, ba, jw, su→en, zh, de, es, ru, ko, fr, ja, pt, tr, pl, ca, nl, ar, sv, it, id, hi, fi, vi, he, uk, el, ms, cs, ro, da, hu, ta, False, th, ur, hr, bg, lt, la, mi, ml, cy, sk, te, fa, lv, bn, sr, az, sl, kn, et, mk, br, eu, is, hy, ne, mn, bs, kk, sq, sw, gl, mr, pa, si, km, sn, yo, so, af, oc, ka, be, tg, sd, gu, am, yi, lo, uz, fo, ht, ps, tk, nn, mt, sa, lb, my, bo, tl, mg, as, tt, haw, ln, ha, ba, jw, suhuggingface
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| OpenAI Platform docs | developers.openai.com/api/docs/deprecations.md | model_docs | T1· Official | 5 min ago | 1 |
| OpenAI Platform docs | developers.openai.com/api/docs/models.md | model_docs | T1· Official | 5 min ago | 1 |
| Groq — docs & pricing | console.groq.com/docs/models | model_docs | T1· Official | 57 min ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/openai/whisper-large-v3 | model_page | T2· Quality secondary | 26 min ago | 3 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/openai/whisper-large-v3-turbo | model_page | T2· Quality secondary | 26 min ago | 3 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=openai&p=0&sort=downloads | listing | T2· Quality secondary | 55 min ago | 3 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/openai/whisper-large-v3/raw/main/README.md | model_card | T2· Quality secondary | 1 h ago | 1 |
Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.