Updated 10 min ago · first seen 11 Sept 2026
model_01M294WZMZ7WPEYGA9XGRZRN9W
- Parameters
- 808.9M
- T2 · 2 h ago
- Released
- 1 Oct 2024
- T2 · 2 h ago
- License
- mit
- T2 · 2 h ago
Specification
- Release date
- 1 Oct 2024
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Openness
- open-weights
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- License
- mit
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
- 808.9M
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 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 2 h agomedium
- Base model
- openai/whisper-large-v3
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- File size
- 1.6 GB
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Hugging Face repo
- openai/whisper-large-v3-turbo
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Pipeline tag
- automatic-speech-recognition
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Model card
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Downloads
- 6,890,829
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 min agomedium
- Likes
- 3,315
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 min agomedium
- Gated
- No
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Groq model id
- whisper-large-v3-turbo
Source:Groq — docs & pricingT1observed 2 h agohigh
- Groq pricing note
- $0.04 per hour
Source:Groq — docs & pricingT1observed 2 h agohigh
- Hf inference providers
- deepinfra, hf-inference
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Last modified
- 2024-10-04T14:51:11+00:00
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Library name
- transformers
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Downloads all time
- 115,915,467
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 10 min agomedium
- Model type
- whisper
Source:Hugging Face Hub (public pages, model cards, papers)T2observed 2 h agomedium
- Tags
- transformers, safetensors, whisper, automatic-speech-recognition, audio, 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
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
23
Source tiers
T1T22 / 21
Freshest observation
10 min ago
Conflicts
None
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 2 h 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 | 1.0 GB | Yes |
| Apple M3 Ultra | 4bit | — | 1.0 GB | Yes |
| Mac Studio (Apple M5 Ultra) | 4bit | — | 1.0 GB | Yes |
| AMD Instinct MI325X | 4bit | 256 GB | 1.0 GB | Yes |
| AMD Instinct MI300X | 4bit | 192 GB | 1.0 GB | Yes |
| Apple M2 Ultra | 4bit | — | 1.0 GB | Yes |
| NVIDIA B200 | 4bit | 180 GB | 1.0 GB | Yes |
| NVIDIA H200 | 4bit | 141 GB | 1.0 GB | Yes |
| NVIDIA H200 NVL | 4bit | 141 GB | 1.0 GB | Yes |
| Apple M1 Ultra | 4bit | — | 1.0 GB | Yes |
| Apple M3 Max | 4bit | — | 1.0 GB | Yes |
| Apple M4 Max | 4bit | — | 1.0 GB | Yes |
| Mac Studio (Apple M5 Max) | 4bit | — | 1.0 GB | Yes |
| MacBook Pro (Apple M5 Max) | 4bit | — | 1.0 GB | Yes |
| NVIDIA DGX Spark | 4bit | 128 GB | 1.0 GB | Yes |
| Apple M2 Max | 4bit | — | 1.0 GB | Yes |
| NVIDIA H100 NVL | 4bit | 94 GB | 1.0 GB | Yes |
| NVIDIA A100 80GB | 4bit | 80 GB | 1.0 GB | Yes |
| NVIDIA H100 SXM | 4bit | 80 GB | 1.0 GB | Yes |
| Apple M1 Max | 4bit | — | 1.0 GB | Yes |
| Apple M4 Pro | 4bit | — | 1.0 GB | Yes |
| Mac mini (Apple M5 Pro) | 4bit | — | 1.0 GB | Yes |
| MacBook Pro (Apple M5 Pro) | 4bit | — | 1.0 GB | Yes |
| Apple M3 Pro | 4bit | — | 1.0 GB | Yes |
| Apple M1 Pro | 4bit | — | 1.0 GB | Yes |
| Apple M2 Pro | 4bit | — | 1.0 GB | Yes |
| Apple M4 | 4bit | — | 1.0 GB | Yes |
| iMac (Apple M4) | 4bit | — | 1.0 GB | Yes |
| Mac mini (Apple M6) | 4bit | — | 1.0 GB | Yes |
| MacBook Air (Apple M5) | 4bit | — | 1.0 GB | Yes |
| MacBook Pro (Apple M5) | 4bit | — | 1.0 GB | Yes |
| NVIDIA GeForce RTX 5090 | 4bit | 32 GB | 1.0 GB | Yes |
| Apple M2 | 4bit | — | 1.0 GB | Yes |
| Apple M3 | 4bit | — | 1.0 GB | Yes |
| NVIDIA GeForce RTX 3090 | 4bit | 24 GB | 1.0 GB | Yes |
| NVIDIA GeForce RTX 4090 | 4bit | 24 GB | 1.0 GB | Yes |
| Apple M1 | 4bit | — | 1.0 GB | Yes |
Ancestors 1
- Whisper1.54B
This model
Whisper Large V3 Turbo
808.9M params
Quantizations 0
None recorded.
Descendants 0
None recorded.
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
Languageslanguages1
| 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 |
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 →
| Source | Document | Type | Tier | Last observed | Snapshots |
|---|---|---|---|---|---|
| Groq — docs & pricing | console.groq.com/docs/models | model_docs | T1· Official | 40 min ago | 2 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/openai/whisper-large-v3-turbo | model_page | T2· Quality secondary | 10 min ago | 3 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/models?author=openai&p=0&sort=downloads | listing | T2· Quality secondary | 39 min ago | 3 |
| Hugging Face Hub (public pages, model cards, papers) | huggingface.co/openai/whisper-large-v3-turbo/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.