Models / whisper

Whisper-Hindi2Hinglish-Prime

Reconstructed from its own config.json with no weights read. 254K downloads on Hugging Face.

Our count against the checkpoint

The left number comes from the graph. The right one is the number of scalars in the published weight files. Nothing on this page was tuned to make them agree.

Derived from structure

1.54B

1,535,882,240 parameters

In the published checkpoint

1.54B

1,543,490,560 scalars · safetensors.total, read 2025-11-06

Delta

-0.49%

What it costs to run

Cost is a roofline estimate on the priced GPU for 10 epochs at batch 32 over 50,000 samples (assumed; no dataset attached). GPU fit is fp32 weights plus gradients plus two Adam moments (16 bytes per parameter) with 1.3x headroom; activations are not included and grow with batch size.

Layers

233

Will it forward-pass

Yes

Priced on

A10G (24GB)

Est. one run

$12.04

Card	Memory
T4 (16GB)	weights + activations	does not fit
A100 (40GB)	weights + activations	fits
H100 (80GB)	weights + activations	fits

Structure

236 nodes. Output shapes are propagated from the input shape, batch dimension excluded.

	Layer	Type	Output shape
1	Input	Input	1 × 512
2	MelSpectrogram	Mel Spectrogram	1 × 80 × 1
3	Enc_Conv1	Conv1D	1 × 1280 × 1
4	Enc_Conv2	Conv1D	1 × 1280 × 1
5	Enc_ToTokens	Permute	1 × 1 × 1280
6	Enc_PosEnc	Positional Encoding	1 × 1 × 1280
7	Enc_Attn_1	Multi-Head Attention	1 × 1 × 1280
8	Enc_Norm_1	LayerNorm	1 × 1 × 1280
9	Enc_FFN_1	Feed Forward	1 × 1 × 1280
10	Enc_Attn_2	Multi-Head Attention	1 × 1 × 1280
11	Enc_Norm_2	LayerNorm	1 × 1 × 1280
12	Enc_FFN_2	Feed Forward	1 × 1 × 1280
13	Enc_Attn_3	Multi-Head Attention	1 × 1 × 1280
14	Enc_Norm_3	LayerNorm	1 × 1 × 1280
15	Enc_FFN_3	Feed Forward	1 × 1 × 1280
16	Enc_Attn_4	Multi-Head Attention	1 × 1 × 1280
17	Enc_Norm_4	LayerNorm	1 × 1 × 1280
18	Enc_FFN_4	Feed Forward	1 × 1 × 1280
19	Enc_Attn_5	Multi-Head Attention	1 × 1 × 1280
20	Enc_Norm_5	LayerNorm	1 × 1 × 1280
21	Enc_FFN_5	Feed Forward	1 × 1 × 1280
22	Enc_Attn_6	Multi-Head Attention	1 × 1 × 1280
23	Enc_Norm_6	LayerNorm	1 × 1 × 1280
24	Enc_FFN_6	Feed Forward	1 × 1 × 1280
25	Enc_Attn_7	Multi-Head Attention	1 × 1 × 1280
26	Enc_Norm_7	LayerNorm	1 × 1 × 1280
27	Enc_FFN_7	Feed Forward	1 × 1 × 1280
28	Enc_Attn_8	Multi-Head Attention	1 × 1 × 1280
29	Enc_Norm_8	LayerNorm	1 × 1 × 1280
30	Enc_FFN_8	Feed Forward	1 × 1 × 1280
31	Enc_Attn_9	Multi-Head Attention	1 × 1 × 1280
32	Enc_Norm_9	LayerNorm	1 × 1 × 1280
33	Enc_FFN_9	Feed Forward	1 × 1 × 1280
34	Enc_Attn_10	Multi-Head Attention	1 × 1 × 1280
35	Enc_Norm_10	LayerNorm	1 × 1 × 1280
36	Enc_FFN_10	Feed Forward	1 × 1 × 1280
37	Enc_Attn_11	Multi-Head Attention	1 × 1 × 1280
38	Enc_Norm_11	LayerNorm	1 × 1 × 1280
39	Enc_FFN_11	Feed Forward	1 × 1 × 1280
40	Enc_Attn_12	Multi-Head Attention	1 × 1 × 1280
41	Enc_Norm_12	LayerNorm	1 × 1 × 1280
42	Enc_FFN_12	Feed Forward	1 × 1 × 1280
43	Enc_Attn_13	Multi-Head Attention	1 × 1 × 1280
44	Enc_Norm_13	LayerNorm	1 × 1 × 1280
45	Enc_FFN_13	Feed Forward	1 × 1 × 1280
46	Enc_Attn_14	Multi-Head Attention	1 × 1 × 1280
47	Enc_Norm_14	LayerNorm	1 × 1 × 1280
48	Enc_FFN_14	Feed Forward	1 × 1 × 1280
49	Enc_Attn_15	Multi-Head Attention	1 × 1 × 1280
50	Enc_Norm_15	LayerNorm	1 × 1 × 1280
51	Enc_FFN_15	Feed Forward	1 × 1 × 1280
52	Enc_Attn_16	Multi-Head Attention	1 × 1 × 1280
53	Enc_Norm_16	LayerNorm	1 × 1 × 1280
54	Enc_FFN_16	Feed Forward	1 × 1 × 1280
55	Enc_Attn_17	Multi-Head Attention	1 × 1 × 1280
56	Enc_Norm_17	LayerNorm	1 × 1 × 1280
57	Enc_FFN_17	Feed Forward	1 × 1 × 1280
58	Enc_Attn_18	Multi-Head Attention	1 × 1 × 1280
59	Enc_Norm_18	LayerNorm	1 × 1 × 1280
60	Enc_FFN_18	Feed Forward	1 × 1 × 1280
61	Enc_Attn_19	Multi-Head Attention	1 × 1 × 1280
62	Enc_Norm_19	LayerNorm	1 × 1 × 1280
63	Enc_FFN_19	Feed Forward	1 × 1 × 1280
64	Enc_Attn_20	Multi-Head Attention	1 × 1 × 1280
65	Enc_Norm_20	LayerNorm	1 × 1 × 1280
66	Enc_FFN_20	Feed Forward	1 × 1 × 1280
67	Enc_Attn_21	Multi-Head Attention	1 × 1 × 1280
68	Enc_Norm_21	LayerNorm	1 × 1 × 1280
69	Enc_FFN_21	Feed Forward	1 × 1 × 1280
70	Enc_Attn_22	Multi-Head Attention	1 × 1 × 1280
71	Enc_Norm_22	LayerNorm	1 × 1 × 1280
72	Enc_FFN_22	Feed Forward	1 × 1 × 1280
73	Enc_Attn_23	Multi-Head Attention	1 × 1 × 1280
74	Enc_Norm_23	LayerNorm	1 × 1 × 1280
75	Enc_FFN_23	Feed Forward	1 × 1 × 1280
76	Enc_Attn_24	Multi-Head Attention	1 × 1 × 1280
77	Enc_Norm_24	LayerNorm	1 × 1 × 1280
78	Enc_FFN_24	Feed Forward	1 × 1 × 1280
79	Enc_Attn_25	Multi-Head Attention	1 × 1 × 1280
80	Enc_Norm_25	LayerNorm	1 × 1 × 1280
81	Enc_FFN_25	Feed Forward	1 × 1 × 1280
82	Enc_Attn_26	Multi-Head Attention	1 × 1 × 1280
83	Enc_Norm_26	LayerNorm	1 × 1 × 1280
84	Enc_FFN_26	Feed Forward	1 × 1 × 1280
85	Enc_Attn_27	Multi-Head Attention	1 × 1 × 1280
86	Enc_Norm_27	LayerNorm	1 × 1 × 1280
87	Enc_FFN_27	Feed Forward	1 × 1 × 1280
88	Enc_Attn_28	Multi-Head Attention	1 × 1 × 1280
89	Enc_Norm_28	LayerNorm	1 × 1 × 1280
90	Enc_FFN_28	Feed Forward	1 × 1 × 1280
91	Enc_Attn_29	Multi-Head Attention	1 × 1 × 1280
92	Enc_Norm_29	LayerNorm	1 × 1 × 1280
93	Enc_FFN_29	Feed Forward	1 × 1 × 1280
94	Enc_Attn_30	Multi-Head Attention	1 × 1 × 1280
95	Enc_Norm_30	LayerNorm	1 × 1 × 1280
96	Enc_FFN_30	Feed Forward	1 × 1 × 1280
97	Enc_Attn_31	Multi-Head Attention	1 × 1 × 1280
98	Enc_Norm_31	LayerNorm	1 × 1 × 1280
99	Enc_FFN_31	Feed Forward	1 × 1 × 1280
100	Enc_Attn_32	Multi-Head Attention	1 × 1 × 1280
101	Enc_Norm_32	LayerNorm	1 × 1 × 1280
102	Enc_FFN_32	Feed Forward	1 × 1 × 1280
103	decoder_tokens	Input	1 × 448
104	Dec_Token_Embedding	Embedding	1 × 448 × 1280
105	Dec_PosEmbedding	Learned Pos Embed	1 × 448 × 1280
106	Dec_SelfAttn_1	Causal Attention	1 × 448 × 1280
107	Dec_CrossAttn_1	Cross-Attention	1 × 448 × 1280
108	Dec_Norm_1	LayerNorm	1 × 448 × 1280
109	Dec_FFN_1	Feed Forward	1 × 448 × 1280
110	Dec_SelfAttn_2	Causal Attention	1 × 448 × 1280
111	Dec_CrossAttn_2	Cross-Attention	1 × 448 × 1280
112	Dec_Norm_2	LayerNorm	1 × 448 × 1280
113	Dec_FFN_2	Feed Forward	1 × 448 × 1280
114	Dec_SelfAttn_3	Causal Attention	1 × 448 × 1280
115	Dec_CrossAttn_3	Cross-Attention	1 × 448 × 1280
116	Dec_Norm_3	LayerNorm	1 × 448 × 1280
117	Dec_FFN_3	Feed Forward	1 × 448 × 1280
118	Dec_SelfAttn_4	Causal Attention	1 × 448 × 1280
119	Dec_CrossAttn_4	Cross-Attention	1 × 448 × 1280
120	Dec_Norm_4	LayerNorm	1 × 448 × 1280
121	Dec_FFN_4	Feed Forward	1 × 448 × 1280
122	Dec_SelfAttn_5	Causal Attention	1 × 448 × 1280
123	Dec_CrossAttn_5	Cross-Attention	1 × 448 × 1280
124	Dec_Norm_5	LayerNorm	1 × 448 × 1280
125	Dec_FFN_5	Feed Forward	1 × 448 × 1280
126	Dec_SelfAttn_6	Causal Attention	1 × 448 × 1280
127	Dec_CrossAttn_6	Cross-Attention	1 × 448 × 1280
128	Dec_Norm_6	LayerNorm	1 × 448 × 1280
129	Dec_FFN_6	Feed Forward	1 × 448 × 1280
130	Dec_SelfAttn_7	Causal Attention	1 × 448 × 1280
131	Dec_CrossAttn_7	Cross-Attention	1 × 448 × 1280
132	Dec_Norm_7	LayerNorm	1 × 448 × 1280
133	Dec_FFN_7	Feed Forward	1 × 448 × 1280
134	Dec_SelfAttn_8	Causal Attention	1 × 448 × 1280
135	Dec_CrossAttn_8	Cross-Attention	1 × 448 × 1280
136	Dec_Norm_8	LayerNorm	1 × 448 × 1280
137	Dec_FFN_8	Feed Forward	1 × 448 × 1280
138	Dec_SelfAttn_9	Causal Attention	1 × 448 × 1280
139	Dec_CrossAttn_9	Cross-Attention	1 × 448 × 1280
140	Dec_Norm_9	LayerNorm	1 × 448 × 1280
141	Dec_FFN_9	Feed Forward	1 × 448 × 1280
142	Dec_SelfAttn_10	Causal Attention	1 × 448 × 1280
143	Dec_CrossAttn_10	Cross-Attention	1 × 448 × 1280
144	Dec_Norm_10	LayerNorm	1 × 448 × 1280
145	Dec_FFN_10	Feed Forward	1 × 448 × 1280
146	Dec_SelfAttn_11	Causal Attention	1 × 448 × 1280
147	Dec_CrossAttn_11	Cross-Attention	1 × 448 × 1280
148	Dec_Norm_11	LayerNorm	1 × 448 × 1280
149	Dec_FFN_11	Feed Forward	1 × 448 × 1280
150	Dec_SelfAttn_12	Causal Attention	1 × 448 × 1280
151	Dec_CrossAttn_12	Cross-Attention	1 × 448 × 1280
152	Dec_Norm_12	LayerNorm	1 × 448 × 1280
153	Dec_FFN_12	Feed Forward	1 × 448 × 1280
154	Dec_SelfAttn_13	Causal Attention	1 × 448 × 1280
155	Dec_CrossAttn_13	Cross-Attention	1 × 448 × 1280
156	Dec_Norm_13	LayerNorm	1 × 448 × 1280
157	Dec_FFN_13	Feed Forward	1 × 448 × 1280
158	Dec_SelfAttn_14	Causal Attention	1 × 448 × 1280
159	Dec_CrossAttn_14	Cross-Attention	1 × 448 × 1280
160	Dec_Norm_14	LayerNorm	1 × 448 × 1280
161	Dec_FFN_14	Feed Forward	1 × 448 × 1280
162	Dec_SelfAttn_15	Causal Attention	1 × 448 × 1280
163	Dec_CrossAttn_15	Cross-Attention	1 × 448 × 1280
164	Dec_Norm_15	LayerNorm	1 × 448 × 1280
165	Dec_FFN_15	Feed Forward	1 × 448 × 1280
166	Dec_SelfAttn_16	Causal Attention	1 × 448 × 1280
167	Dec_CrossAttn_16	Cross-Attention	1 × 448 × 1280
168	Dec_Norm_16	LayerNorm	1 × 448 × 1280
169	Dec_FFN_16	Feed Forward	1 × 448 × 1280
170	Dec_SelfAttn_17	Causal Attention	1 × 448 × 1280
171	Dec_CrossAttn_17	Cross-Attention	1 × 448 × 1280
172	Dec_Norm_17	LayerNorm	1 × 448 × 1280
173	Dec_FFN_17	Feed Forward	1 × 448 × 1280
174	Dec_SelfAttn_18	Causal Attention	1 × 448 × 1280
175	Dec_CrossAttn_18	Cross-Attention	1 × 448 × 1280
176	Dec_Norm_18	LayerNorm	1 × 448 × 1280
177	Dec_FFN_18	Feed Forward	1 × 448 × 1280
178	Dec_SelfAttn_19	Causal Attention	1 × 448 × 1280
179	Dec_CrossAttn_19	Cross-Attention	1 × 448 × 1280
180	Dec_Norm_19	LayerNorm	1 × 448 × 1280
181	Dec_FFN_19	Feed Forward	1 × 448 × 1280
182	Dec_SelfAttn_20	Causal Attention	1 × 448 × 1280
183	Dec_CrossAttn_20	Cross-Attention	1 × 448 × 1280
184	Dec_Norm_20	LayerNorm	1 × 448 × 1280
185	Dec_FFN_20	Feed Forward	1 × 448 × 1280
186	Dec_SelfAttn_21	Causal Attention	1 × 448 × 1280
187	Dec_CrossAttn_21	Cross-Attention	1 × 448 × 1280
188	Dec_Norm_21	LayerNorm	1 × 448 × 1280
189	Dec_FFN_21	Feed Forward	1 × 448 × 1280
190	Dec_SelfAttn_22	Causal Attention	1 × 448 × 1280
191	Dec_CrossAttn_22	Cross-Attention	1 × 448 × 1280
192	Dec_Norm_22	LayerNorm	1 × 448 × 1280
193	Dec_FFN_22	Feed Forward	1 × 448 × 1280
194	Dec_SelfAttn_23	Causal Attention	1 × 448 × 1280
195	Dec_CrossAttn_23	Cross-Attention	1 × 448 × 1280
196	Dec_Norm_23	LayerNorm	1 × 448 × 1280
197	Dec_FFN_23	Feed Forward	1 × 448 × 1280
198	Dec_SelfAttn_24	Causal Attention	1 × 448 × 1280
199	Dec_CrossAttn_24	Cross-Attention	1 × 448 × 1280
200	Dec_Norm_24	LayerNorm	1 × 448 × 1280
201	Dec_FFN_24	Feed Forward	1 × 448 × 1280
202	Dec_SelfAttn_25	Causal Attention	1 × 448 × 1280
203	Dec_CrossAttn_25	Cross-Attention	1 × 448 × 1280
204	Dec_Norm_25	LayerNorm	1 × 448 × 1280
205	Dec_FFN_25	Feed Forward	1 × 448 × 1280
206	Dec_SelfAttn_26	Causal Attention	1 × 448 × 1280
207	Dec_CrossAttn_26	Cross-Attention	1 × 448 × 1280
208	Dec_Norm_26	LayerNorm	1 × 448 × 1280
209	Dec_FFN_26	Feed Forward	1 × 448 × 1280
210	Dec_SelfAttn_27	Causal Attention	1 × 448 × 1280
211	Dec_CrossAttn_27	Cross-Attention	1 × 448 × 1280
212	Dec_Norm_27	LayerNorm	1 × 448 × 1280
213	Dec_FFN_27	Feed Forward	1 × 448 × 1280
214	Dec_SelfAttn_28	Causal Attention	1 × 448 × 1280
215	Dec_CrossAttn_28	Cross-Attention	1 × 448 × 1280
216	Dec_Norm_28	LayerNorm	1 × 448 × 1280
217	Dec_FFN_28	Feed Forward	1 × 448 × 1280
218	Dec_SelfAttn_29	Causal Attention	1 × 448 × 1280
219	Dec_CrossAttn_29	Cross-Attention	1 × 448 × 1280
220	Dec_Norm_29	LayerNorm	1 × 448 × 1280
221	Dec_FFN_29	Feed Forward	1 × 448 × 1280
222	Dec_SelfAttn_30	Causal Attention	1 × 448 × 1280
223	Dec_CrossAttn_30	Cross-Attention	1 × 448 × 1280
224	Dec_Norm_30	LayerNorm	1 × 448 × 1280
225	Dec_FFN_30	Feed Forward	1 × 448 × 1280
226	Dec_SelfAttn_31	Causal Attention	1 × 448 × 1280
227	Dec_CrossAttn_31	Cross-Attention	1 × 448 × 1280
228	Dec_Norm_31	LayerNorm	1 × 448 × 1280
229	Dec_FFN_31	Feed Forward	1 × 448 × 1280
230	Dec_SelfAttn_32	Causal Attention	1 × 448 × 1280
231	Dec_CrossAttn_32	Cross-Attention	1 × 448 × 1280
232	Dec_Norm_32	LayerNorm	1 × 448 × 1280
233	Dec_FFN_32	Feed Forward	1 × 448 × 1280
234	Dec_Norm_Final	LayerNorm	1 × 448 × 1280
235	LM_Head	Linear	1 × 448 × 51866
236	Output	Output	1 × 448 × 51866

What the verifier says

infoAt 64 stacked attention layers, residual-branch outputs add up; unscaled init lets activation variance grow with depth. GPT-2/LLaMA-family models scale the residual projections by depth (N(0, 0.02 / √(2L))). Fix: Scale residual output projections by depth: nn.init.normal_(w, std=0.02 / math.sqrt(2 * n_layers))
deep-attention-default-init

Do this to your own model

Same numbers, on a model in your repo, in one command. No account.

pip install neurarch-trace
neurarch-trace Oriserve/Whisper-Hindi2Hinglish-Prime --plan --share

Paste a model instead Markdown twin Index JSON POST /api/v1/plan

Other whisper checkpoints

Whisper-Hindi2Hinglish-Apex

801M derived · -0.91% against the checkpoint

whisper-large-v3

1.54B derived · -0.49% against the checkpoint

whisper-large-v3-turbo

801M derived · -0.91% against the checkpoint