Promethic commited on
Commit
d9b5cf0
·
verified ·
1 Parent(s): 1172b6d

Emberon-2: 350M dictation-cleanup model (v4.5.1)

Browse files
Files changed (6) hide show
  1. .gitattributes +2 -0
  2. Emberon-2-F16.gguf +3 -0
  3. Emberon-2-Q4_K_M.gguf +3 -0
  4. LICENSE +71 -0
  5. NOTICE +37 -0
  6. README.md +189 -0
.gitattributes CHANGED
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ Emberon-2-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
37
+ Emberon-2-F16.gguf filter=lfs diff=lfs merge=lfs -text
Emberon-2-F16.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:056a4b0889eb5b9873d9f38393f5e595fb58c6ffd82b47fde76b9169f602f5a1
3
+ size 711485248
Emberon-2-Q4_K_M.gguf ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18fead8b8df3808ed47a84cd41a5a0617e3374d1a62dd52e3ba4bfb839810ffd
3
+ size 199996928
LICENSE ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ LFM Open License v1.0
2
+
3
+ TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
4
+
5
+ 1. Definitions.
6
+
7
+ "License" shall mean the terms and conditions for use, reproduction, and distribution as defined by this document.
8
+
9
+ "Licensor" shall mean Liquid AI, Inc.
10
+
11
+ "Legal Entity" shall mean the union of the acting entity and all other entities that control, are controlled by, or are under common control with that entity. For the purposes of this definition, "control" means (i) the power, direct or indirect, to cause the direction or management of such entity, whether by contract or otherwise, or (ii) ownership of fifty percent (50%) or more of the outstanding shares, or (iii) beneficial ownership of such entity.
12
+
13
+ "You" (or "Your") shall mean an individual or Legal Entity exercising permissions granted by this License.
14
+
15
+ "Source" form shall mean the preferred form for making modifications, including but not limited to software source code, documentation source, and configuration files.
16
+
17
+ "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation, and conversions to other media types.
18
+
19
+ "Work" shall mean the work of authorship, whether in Source or Object form, made available under the License, as indicated by a copyright notice that is included in or attached to the work.
20
+
21
+ "Derivative Works" shall mean any work, whether in Source or Object form, that is based on (or derived from) the Work and for which the editorial revisions, annotations, elaborations, or other modifications represent, as a whole, an original work of authorship. For the purposes of this License, Derivative Works shall not include works that remain separable from, or merely link (or bind by name) to the interfaces of, the Work and Derivative Works thereof.
22
+
23
+ "Contribution" shall mean any work of authorship, including the original version of the Work and any modifications or additions to that Work or Derivative Works thereof, that is intentionally submitted to Licensor for inclusion in the Work by the copyright owner or by an individual or Legal Entity authorized to submit on behalf of the copyright owner. For the purposes of this definition, "submitted" means any form of electronic, verbal, or written communication sent to the Licensor or its representatives, including but not limited to communication on electronic mailing lists, source code control systems, and issue tracking systems that are managed by, or on behalf of, the Licensor for the purpose of discussing and improving the Work, but excluding communication that is conspicuously marked or otherwise designated in writing by the copyright owner as "Not a Contribution."
24
+
25
+ "Contributor" shall mean Licensor and any individual or Legal Entity on behalf of whom a Contribution has been received by Licensor and subsequently incorporated within the Work.
26
+
27
+ "Commercial Use" shall mean any use of the Work for direct or indirect commercial advantage or monetary compensation.
28
+
29
+ "Qualified Non-Profit Organization" shall mean a Legal Entity that is organized and operated exclusively for religious, charitable, scientific, testing for public safety, literary, or educational purposes, and which is exempt from federal income tax under Section 501(c)(3) of the United States Internal Revenue Code of 1986, as amended, or any equivalent non-profit or charitable organization in a foreign jurisdiction.
30
+
31
+ "Non-Commercial or Research Purposes" shall mean purposes that do not involve any use of the Work or a Derivative Work for Commercial Use.
32
+
33
+ "Threshold" shall mean annual revenue of 10 million United States dollars ($10,000,000) or more.
34
+
35
+ 2. Grant of Copyright License. Subject to the terms and conditions of this License, including the Commercial Use limitation set forth in Section 5, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable copyright license to reproduce, prepare Derivative Works of, publicly display, publicly perform, sublicense, and distribute the Work and such Derivative Works in Source or Object form.
36
+
37
+ 3. Grant of Patent License. Subject to the terms and conditions of this License, including the Commercial Use limitation set forth in Section 5, each Contributor hereby grants to You a perpetual, worldwide, non-exclusive, no-charge, royalty-free, irrevocable (except as stated in this section) patent license to make, have made, use, offer to sell, sell, import, and otherwise transfer the Work, where such license applies only to those patent claims licensable by such Contributor that are necessarily infringed by their Contribution(s) alone or by combination of their Contribution(s) with the Work to which such Contribution(s) was submitted. If You institute patent litigation against any entity (including a cross-claim or counterclaim in a lawsuit) alleging that the Work or a Contribution incorporated within the Work constitutes direct or contributory patent infringement, then any patent licenses granted to You under this License for that Work shall terminate as of the date such litigation is filed.
38
+
39
+ 4. Redistribution. You may reproduce and distribute copies of the Work or Derivative Works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions:
40
+
41
+ (a) You must give any other recipients of the Work or Derivative Works a copy of this License; and
42
+
43
+ (b) You must cause any modified files to carry prominent notices stating that You changed the files; and
44
+
45
+ (c) You must retain, in the Source form of any Derivative Works that You distribute, all copyright, patent, trademark, and attribution notices from the Source form of the Work, excluding those notices that do not pertain to any part of the Derivative Works; and
46
+
47
+ (d) If the Work includes a "NOTICE" text file as part of its distribution, then any Derivative Works that You distribute must include a readable copy of the attribution notices contained within such NOTICE file, excluding those notices that do not pertain to any part of the Derivative Works, in at least one of the following places: within a NOTICE text file distributed as part of the Derivative Works; within the Source form or documentation, if provided along with the Derivative Works; or, within a display generated by the Derivative Works, if and wherever such third-party notices normally appear. The contents of the NOTICE file are for informational purposes only and do not modify the License. You may add Your own attribution notices within Derivative Works that You distribute, alongside or as an addendum to the NOTICE text from the Work, provided that such additional attribution notices cannot be construed as modifying the License.
48
+
49
+ You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such Derivative Works as a whole, provided Your use, reproduction, and distribution of the Work otherwise complies with the conditions stated in this License.
50
+
51
+ 5. Commercial Use Limitation.
52
+
53
+ (a) The rights granted under this License for Commercial Use are conditioned upon You or Your Legal Entity not exceeding the Threshold.
54
+
55
+ (b) Any Commercial Use of the Work or a Derivative Work by a Legal Entity that exceeds the Threshold is not licensed under this Agreement.
56
+
57
+ (c) The Threshold shall not apply to a Qualified Non-Profit Organization's use of the Work or a Derivative Work for Non-Commercial or Research Purposes.
58
+
59
+ 6. Submission of Contributions. Unless You explicitly state otherwise, any Contribution intentionally submitted for inclusion in the Work by You to the Licensor shall be under the terms and conditions of this License, without any additional terms or conditions. Notwithstanding the above, nothing herein shall supersede or modify the terms of any separate license agreement you may have executed with Licensor regarding such Contributions.
60
+
61
+ 7. Trademarks. This License does not grant permission to use the trade names, trademarks, service marks, or product names of the Licensor, except for the reasonable and customary use in describing the origin of the Work and reproducing the content of the NOTICE file.
62
+
63
+ 8. Disclaimer of Warranty. Unless required by applicable law or agreed to in writing, Licensor provides the Work (and each Contributor provides its Contributions) on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied, including, without limitation, any warranties or conditions of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A PARTICULAR PURPOSE. You are solely responsible for determining the appropriateness of using or redistributing the Work and assume any risks associated with Your exercise of permissions under this License.
64
+
65
+ 9. Limitation of Liability. In no event and under no legal theory, whether in tort (including negligence), contract, or otherwise, unless required by applicable law (such as deliberate and grossly negligent acts) or agreed to in writing, shall any Contributor be liable to You for damages, including any direct, indirect, special, incidental, or consequential damages of any character arising as a result of this License or out of the use or inability to use the Work (including but not limited to damages for loss of goodwill, work stoppage, computer failure or malfunction, or any and all other commercial damages or losses), even if such Contributor has been advised of the possibility of such damages.
66
+
67
+ 10. Accepting Warranty or Additional Liability. While redistributing the Work or Derivative Works thereof, You may choose to offer, and charge a fee for, acceptance of support, warranty, indemnity, or other liability obligations and/or rights consistent with this License. However, in accepting such obligations, You may act only on Your own behalf and on Your sole responsibility, not on behalf of any other Contributor, and only if You agree to indemnify, defend, and hold each Contributor harmless for any liability incurred by, or claims asserted against, such Contributor by reason of your accepting any such warranty or additional liability.
68
+
69
+ 11. Termination. This License will terminate automatically and immediately if You fail to comply with any of its terms and conditions. Upon termination, You must cease all use of the Work and any Derivative Works and delete all copies in Your possession.
70
+
71
+ END OF TERMS AND CONDITIONS
NOTICE ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ Emberon-2
2
+ =========
3
+
4
+ Emberon-2 is a fine-tune (LoRA, fused; two training runs averaged) of:
5
+
6
+ LiquidAI/LFM2.5-350M
7
+ Copyright © Liquid AI
8
+ Licensed under the LFM Open License v1.0 (see LICENSE; https://www.liquid.ai/lfm-license)
9
+
10
+ This product includes a MODIFIED version of LFM2.5-350M. The model weights were adapted by
11
+ Promethic Labs to perform dictation cleanup (rewriting raw voice transcripts into clean text
12
+ without answering or executing them), and the 4-bit file's vocabulary was trimmed to the tokens
13
+ English dictation uses. The base architecture and pretrained weights are the work of Liquid AI;
14
+ the modification is the work of Promethic Labs.
15
+
16
+ Modifications © 2026 Promethic Labs (https://wispercode.com)
17
+
18
+ In accordance with Section 4 of the LFM Open License v1.0:
19
+ - a copy of the License is included (see LICENSE);
20
+ - the original attribution/copyright notices are retained (above);
21
+ - this NOTICE states that the files were changed from the original.
22
+
23
+ ATTRIBUTION
24
+ -----------
25
+ REQUIRED (redistribution & derivatives): If you redistribute these weights, or release a
26
+ fine-tune, merge, quantization, or other derivative of Emberon-2, you must retain this NOTICE
27
+ and the copyright notices above (BOTH Liquid AI and Promethic Labs), state that you modified
28
+ the model, and include the LICENSE.
29
+
30
+ REQUESTED (use in products, services, or research): Please credit Promethic Labs. Suggested
31
+ credit line:
32
+
33
+ Powered by Emberon-2 by Promethic Labs (https://promethic.xyz): a dictation-cleanup
34
+ fine-tune of LiquidAI/LFM2.5-350M.
35
+
36
+ Trademarks: "Liquid AI" and "LFM" are trademarks of Liquid AI. "Promethic Labs", "Emberon",
37
+ and "WisperCode" are trademarks of Promethic Labs. Use of a name does not imply endorsement.
README.md ADDED
@@ -0,0 +1,189 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: other
3
+ license_name: lfm1.0
4
+ license_link: LICENSE
5
+ base_model: LiquidAI/LFM2.5-350M
6
+ base_model_relation: finetune
7
+ library_name: gguf
8
+ pipeline_tag: text-generation
9
+ language:
10
+ - en
11
+ tags:
12
+ - dictation
13
+ - voice
14
+ - speech-postprocessing
15
+ - text-cleanup
16
+ - lfm2
17
+ - gguf
18
+ - llama-cpp
19
+ - on-device
20
+ model_name: Emberon-2
21
+ ---
22
+
23
+ # Emberon-2
24
+
25
+ **A 350M-parameter, open-weights model that *cleans up dictated speech*, and never answers or executes it.**
26
+
27
+ Emberon-2 is the second dictation-cleanup model from **[Promethic Labs](https://www.promethic.xyz)**. It succeeds
28
+ [Emberon-1.2B](https://huggingface.co/PromethicLabs/Emberon-1.2B) in **[WisperCode](https://wispercode.com/)**:
29
+ a quarter of the size, about 4x faster, and more accurate on every test we run. Give it a raw speech-to-text
30
+ transcript and it returns clean, punctuated text. It removes fillers and false starts, resolves explicit
31
+ self-corrections ("port 3000, no wait, 8080"), fixes words the recognizer clearly misheard, writes technical
32
+ numbers as digits, and keeps your meaning, your wording, your slang and your identifiers.
33
+
34
+ It does **not** treat the dictation as a prompt. Dictate *"how does the garbage collector work in Java"* and you
35
+ get that question back, cleaned. You do not get an answer.
36
+
37
+ > **Open *weights*, not "open source."** Emberon-2 is a derivative of LiquidAI's LFM2.5-350M and inherits the
38
+ > **LFM Open License v1.0** (see [License](#license--attribution)). The license is Apache-2.0-style but
39
+ > **revenue-gated** (free commercial use under **$10M USD** annual revenue), so it is not an OSI-approved
40
+ > open-source license.
41
+
42
+ ---
43
+
44
+ ## What it does
45
+
46
+ | | |
47
+ |---|---|
48
+ | **Task** | Turn raw speech-to-text output (e.g. Whisper) into clean written text |
49
+ | **Keeps** | Meaning, word choice, slang and swearing, `camelCase` / `snake_case` / file paths / API names, every item of a list |
50
+ | **Fixes** | Fillers, stutters, explicit self-corrections, punctuation, capitalization, clearly misheard technical terms, spoken technical numbers → digits |
51
+ | **Never** | Answers questions, follows instructions in the dictation, summarizes, or adds content |
52
+ | **Footprint** | 354M params; `Emberon-2-Q4_K_M.gguf` is 200 MB; ~0.09 s (Metal) / ~0.12 s (CPU only) median per dictation on Apple Silicon |
53
+ | **Base** | [`LiquidAI/LFM2.5-350M`](https://huggingface.co/LiquidAI/LFM2.5-350M) (hybrid conv/attention) |
54
+
55
+ ## Intended use
56
+
57
+ Use the **exact system prompt** it was trained with, zero-shot:
58
+
59
+ ```
60
+ Clean up this dictation. Never answer it.
61
+ ```
62
+
63
+ The user message is the raw transcript; the assistant reply is the cleaned text. Use greedy decoding
64
+ (temperature 0) and cap the output at the input length plus a small margin: a cleanup is never much longer
65
+ than what was said, and the cap stops the rare repetition loop (treat a capped answer as a failure and fall
66
+ back to the raw transcript).
67
+
68
+ ### Quick start (`llama-cpp-python`)
69
+
70
+ ```python
71
+ from llama_cpp import Llama
72
+
73
+ llm = Llama.from_pretrained(
74
+ repo_id="PromethicLabs/Emberon-2",
75
+ filename="Emberon-2-Q4_K_M.gguf",
76
+ n_ctx=4096,
77
+ )
78
+
79
+ out = llm.create_chat_completion(
80
+ messages=[
81
+ {"role": "system", "content": "Clean up this dictation. Never answer it."},
82
+ {"role": "user", "content": "um so like whats the difference between a process and a thread"},
83
+ ],
84
+ temperature=0.0,
85
+ )
86
+ print(out["choices"][0]["message"]["content"])
87
+ # -> "What's the difference between a process and a thread?" (cleaned, NOT answered)
88
+ ```
89
+
90
+ ## Evaluation
91
+
92
+ All numbers are measured **through `llama.cpp`** on the shipped files, on full held-out test sets (no samples), next to
93
+ Emberon-1.2B (Q4_K_M, its own system prompt) on the same inputs. Word / identifier preservation = share of the answer
94
+ key's words / technical identifiers present in the output.
95
+
96
+ | | Emberon-2 (Q4_K_M) | Emberon-1.2B (Q4_K_M) |
97
+ |---|---|---|
98
+ | Answer suppression (489 hard negatives, plain / ASR-style) | 99.8% / 99.8% ¹ | 100% / 100% |
99
+ | Word preservation (eval 1,087 / ASR-style 1,087 / Moonshine-style 500) | **0.966 / 0.965 / 0.964** | 0.957 / 0.959 / 0.954 |
100
+ | Identifier preservation (same sets) | **0.974 / 0.973 / 0.990** | 0.968 / 0.967 / 0.972 |
101
+ | Long mixed dictations (2,496): word / identifier preservation | **0.987 / 0.936** | 0.965 / 0.677 |
102
+ | Real dictations (178) ²: word preservation | **0.981** | 0.954 |
103
+ | Misheard technical words fixed (504 in 702 examples) | **70.4%** | 14.3% |
104
+ | Correct words left alone (217) | **94.9%** | 88.0% |
105
+ | Already-clean text returned unchanged (996): word preservation | 0.998 | – |
106
+ | Hallucinated content | 0% | 0% |
107
+ | Outputs cut off at the length cap (all sets) | **0** | 14 |
108
+
109
+ ¹ One of 489 is flagged: *"is this an n plus one query"* comes back as *"Is this an NPlus1 query?"*: a formatting
110
+ slip, not an answer. The suppression check is strict on any rewrite of a question.
111
+
112
+ ² Recordings of real dictation, transcribed by a different speech recognizer than the one in training. Most of the
113
+ same recordings are in the training data (as another recognizer's transcript), so treat this row as a sanity check,
114
+ not a held-out score. Both models saw real dictation logs in training.
115
+
116
+ ### Speed and memory (Apple Silicon, `llama.cpp`)
117
+
118
+ | | Emberon-2 | Emberon-1.2B |
119
+ |---|---|---|
120
+ | Median / p95 latency, Metal | **0.088 s / 0.305 s** | 0.391 s / 1.032 s |
121
+ | Median / p95 latency, CPU only | **0.115 s / 0.369 s** | 0.556 s / 1.375 s |
122
+ | File size | **200 MB** | 697 MB |
123
+
124
+ The Q4_K_M file uses a **trimmed vocabulary** (32,158 of the base model's 65,536 tokens, keeping the ones English
125
+ dictation uses plus the byte tokens, so any text still encodes) and an importance-matrix quantization calibrated
126
+ on dictation text. Both cut size and latency with no measurable accuracy loss on our tests.
127
+
128
+ ## Training
129
+
130
+ - **Method:** LoRA (rank 16, scale 1.0, dropout 0) on attention, conv and FFN projections; two runs (plain loss, and
131
+ a loss that up-weights the tokens where the answer differs from the transcript) averaged weight-by-weight, then
132
+ converted to GGUF. One pass over the data, cosine learning-rate decay 2e-4 → 2e-5 after 500 warm-up steps,
133
+ max sequence length 2,048, prompt-masked loss. Trained with **[MLX](https://github.com/ml-explore/mlx)** on Apple
134
+ Silicon from `mlx-community/LFM2.5-350M-bf16`.
135
+ - **Data:** **75,000 examples**, about 96% **synthetic** (written by Claude and OpenAI GPT models to target specific
136
+ behaviours: self-corrections, misheard terms, spoken numbers, slang and swearing kept verbatim, list items kept,
137
+ answer-temptation questions and commands, already-clean text left alone), each screened by an automated checker
138
+ (content preservation, identifier and number checks, leakage and duplicate checks against every test set) and,
139
+ for the newest batches, an LLM answer-key audit. Plus ~1,600 speech-recognizer transcripts of read-aloud narration
140
+ (restraint examples) and ~1,200 real dictation logs. About 18% of the inputs are re-rendered in the
141
+ style of Whisper base.en output, which is what the model sees in the app.
142
+
143
+ ## Files
144
+
145
+ | File | Size | Precision | SHA-256 |
146
+ |---|---|---|---|
147
+ | `Emberon-2-Q4_K_M.gguf` | 199,996,928 B (200 MB) | 4-bit, trimmed vocabulary (recommended) | `18fead8b8df3808ed47a84cd41a5a0617e3374d1a62dd52e3ba4bfb839810ffd` |
148
+ | `Emberon-2-F16.gguf` | 711,485,248 B (711 MB) | 16-bit, full vocabulary (for re-quantization or further fine-tuning) | `056a4b0889eb5b9873d9f38393f5e595fb58c6ffd82b47fde76b9169f602f5a1` |
149
+
150
+ ## Limitations & responsible use
151
+
152
+ - **Mostly synthetic tests.** Most held-out sets are synthetic (same generation process as training, zero overlap).
153
+ The real-dictation signal (a blind side-by-side review against the previous model on 255 real recordings, 62 of
154
+ them never trained on: even on meaning kept) is encouraging but small.
155
+ - **English, technical flavour.** Tuned for English dictation, especially software work. Other languages are out
156
+ of scope, and the trimmed vocabulary makes the Q4_K_M file a poor starting point for them (use the F16).
157
+ - **It can still drop content.** On long, rambling dictations it occasionally drops a restated phrase or a
158
+ clause. Keep the raw transcript available if every word matters.
159
+ - **It is a cleanup tool, not an assistant.** By design it will not answer, summarize, translate, or act on the text.
160
+
161
+ ## License & attribution
162
+
163
+ Emberon-2 is a fine-tune of **`LiquidAI/LFM2.5-350M`** and is released under the **LFM Open License v1.0**,
164
+ inherited from the base model. The full license text is in [`LICENSE`](./LICENSE).
165
+
166
+ - **Free commercial use is limited to entities under $10,000,000 USD annual revenue.** Above that threshold,
167
+ commercial use requires a separate license from Liquid AI.
168
+ - When redistributing you must keep the attribution notices, **state that the model was modified**, and include a
169
+ copy of the license. See [`LICENSE`](./LICENSE) and [`NOTICE`](./NOTICE).
170
+
171
+ > Base model © Liquid AI, licensed under the LFM Open License v1.0.
172
+ > **Modifications (dictation-cleanup fine-tune) © 2026 Promethic Labs.** This is a modified version of LFM2.5-350M.
173
+
174
+ **Please credit Promethic Labs** if Emberon-2 powers a product, service, or paper. Suggested credit line:
175
+
176
+ > Powered by **Emberon-2** by [Promethic Labs](https://www.promethic.xyz): a dictation-cleanup fine-tune of
177
+ > LiquidAI/LFM2.5-350M.
178
+
179
+ ## Citation
180
+
181
+ ```bibtex
182
+ @misc{emberon2_2026,
183
+ title = {Emberon-2: a 350M dictation-cleanup model that cleans speech without answering it},
184
+ author = {Promethic Labs},
185
+ year = {2026},
186
+ note = {Fine-tune of LiquidAI/LFM2.5-350M under the LFM Open License v1.0},
187
+ url = {https://huggingface.co/PromethicLabs/Emberon-2}
188
+ }
189
+ ```