final

.gitattributes

@@ -36,3 +36,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 qwen3.5-2b/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 gemma-3-1b-it/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 qwen3.5-2b-50pct-masked-weighted/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+edit-qwen3.5-2b/test_eval/predictions.jsonl filter=lfs diff=lfs merge=lfs -text
+edit-qwen3.5-2b/tokenizer.json filter=lfs diff=lfs merge=lfs -text

edit-qwen3.5-2b/README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen3.5-2B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3.5-2B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.21.0

edit-qwen3.5-2b/adapter_config.json

@@ -0,0 +1,56 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3.5-2B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "up_proj",
+    "v_proj",
+    "in_proj_b",
+    "in_proj_z",
+    "o_proj",
+    "out_proj",
+    "in_proj_a",
+    "k_proj",
+    "in_proj_qkv",
+    "down_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

edit-qwen3.5-2b/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1728f9a704086e3589352b594b5e256dd7ff4e42ba8b23422f3b074bc59efce
+size 134604152

edit-qwen3.5-2b/chat_template.jinja

@@ -0,0 +1,154 @@
+{%- set image_count = namespace(value=0) %}
+{%- set video_count = namespace(value=0) %}
+{%- macro render_content(content, do_vision_count, is_system_content=false) %}
+    {%- if content is string %}
+        {{- content }}
+    {%- elif content is iterable and content is not mapping %}
+        {%- for item in content %}
+            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain images.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set image_count.value = image_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Picture ' ~ image_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}
+            {%- elif 'video' in item or item.type == 'video' %}
+                {%- if is_system_content %}
+                    {{- raise_exception('System message cannot contain videos.') }}
+                {%- endif %}
+                {%- if do_vision_count %}
+                    {%- set video_count.value = video_count.value + 1 %}
+                {%- endif %}
+                {%- if add_vision_id %}
+                    {{- 'Video ' ~ video_count.value ~ ': ' }}
+                {%- endif %}
+                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}
+            {%- elif 'text' in item %}
+                {{- item.text }}
+            {%- else %}
+                {{- raise_exception('Unexpected item type in content.') }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif content is none or content is undefined %}
+        {{- '' }}
+    {%- else %}
+        {{- raise_exception('Unexpected content type.') }}
+    {%- endif %}
+{%- endmacro %}
+{%- if not messages %}
+    {{- raise_exception('No messages provided.') }}
+{%- endif %}
+{%- if tools and tools is iterable and tools is not mapping %}
+    {{- '<|im_start|>system\n' }}
+    {{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {%- if content %}
+            {{- '\n\n' + content }}
+        {%- endif %}
+    {%- endif %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {%- set content = render_content(messages[0].content, false, true)|trim %}
+        {{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" %}
+        {%- set content = render_content(message.content, false)|trim %}
+        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
+            {%- set ns.multi_step_tool = false %}
+            {%- set ns.last_query_index = index %}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if ns.multi_step_tool %}
+    {{- raise_exception('No user query found in messages.') }}
+{%- endif %}
+{%- for message in messages %}
+    {%- set content = render_content(message.content, true)|trim %}
+    {%- if message.role == "system" %}
+        {%- if not loop.first %}
+            {{- raise_exception('System message must be at the beginning.') }}
+        {%- endif %}
+    {%- elif message.role == "user" %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- set reasoning_content = reasoning_content|trim %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if tool_call.function is defined %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {%- if loop.first %}
+                    {%- if content|trim %}
+                        {{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- else %}
+                        {{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                    {%- endif %}
+                {%- else %}
+                    {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+                {%- endif %}
+                {%- if tool_call.arguments is defined %}
+                    {%- for args_name, args_value in tool_call.arguments|items %}
+                        {{- '<parameter=' + args_name + '>\n' }}
+                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                        {{- args_value }}
+                        {{- '\n</parameter>\n' }}
+                    {%- endfor %}
+                {%- endif %}
+                {{- '</function>\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- raise_exception('Unexpected message role.') }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is true %}
+        {{- '<think>\n' }}
+    {%- else %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

edit-qwen3.5-2b/tb/events.out.tfevents.1790604388.9b7939721266.4215.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef4878f89b7d5d077edeb7c9bce5f060004e2d63825b1031c34f943ff92d62d0
-size 19324
+oid sha256:05767c145c43784b0f21ed56b6ed7460795e48bd53e9cd1111c349bb752bedb6
+size 19678

edit-qwen3.5-2b/test_eval/baselines.json

@@ -0,0 +1,50 @@
+{
+  "whisper": {
+    "n_examples": 1978,
+    "wer": 0.19286111707900203,
+    "wer_zwnj_normalized": 0.18077200636819868,
+    "exact_match": 0.006066734074823054,
+    "hallucination_rate": 0.0,
+    "rows_changed": 0.0,
+    "fix_rate": 0.0,
+    "preservation_rate": 1.0,
+    "targeted_score": 0.5,
+    "fix_rate_lenient": 0.0,
+    "preservation_rate_lenient": 1.0,
+    "targeted_score_lenient": 0.5,
+    "fixed_lenient": 0,
+    "broken_lenient": 0,
+    "net_fixed_lenient": 0,
+    "broken_per_100_correct": 0.0,
+    "fix_rate_recoverable": 0.0,
+    "unrecoverable_targets": 966,
+    "entity_fix_rate": 0.0,
+    "entity_keep_rate": 1.0,
+    "entity_spans_whisper_wrong": 57,
+    "entity_spans_whisper_right": 217
+  },
+  "rules": {
+    "n_examples": 1978,
+    "wer": 0.18624502140177493,
+    "wer_zwnj_normalized": 0.17446440474419783,
+    "exact_match": 0.006572295247724975,
+    "hallucination_rate": 0.0,
+    "rows_changed": 0.6875631951466128,
+    "fix_rate": 0.05559820155718829,
+    "preservation_rate": 0.9996089846635096,
+    "targeted_score": 0.5276035931103489,
+    "fix_rate_lenient": 0.05892479464856623,
+    "preservation_rate_lenient": 0.9995903045402917,
+    "targeted_score_lenient": 0.5292575495944289,
+    "fixed_lenient": 3594,
+    "broken_lenient": 123,
+    "net_fixed_lenient": 3471,
+    "broken_per_100_correct": 0.04096954597082835,
+    "fix_rate_recoverable": 0.059573192063571395,
+    "unrecoverable_targets": 966,
+    "entity_fix_rate": 0.0,
+    "entity_keep_rate": 1.0,
+    "entity_spans_whisper_wrong": 57,
+    "entity_spans_whisper_right": 217
+  }
+}

edit-qwen3.5-2b/test_eval/comparison.md

@@ -0,0 +1,11 @@
+| slice | method | WER | fixed | broken | net | broken/100 | entity fix | rows changed |
+|---|---|---|---|---|---|---|---|---|
+| main | whisper | 0.1929 | 0 | 0 | 0 | 0.00 | 0.000 | 0.000 |
+| main | rules | 0.1862 | 3594 | 123 | 3471 | 0.04 | 0.000 | 0.688 |
+| main | model | 0.1863 | 3603 | 136 | 3467 | 0.05 | 0.018 | 0.694 |
+| entity | whisper | 0.1866 | 0 | 0 | 0 | 0.00 | 0.000 | 0.000 |
+| entity | rules | 0.1800 | 1833 | 49 | 1784 | 0.03 | 0.000 | 0.715 |
+| entity | model | 0.1800 | 1838 | 58 | 1780 | 0.04 | 0.018 | 0.723 |
+| typo | whisper | 0.1412 | 0 | 0 | 0 | 0.00 | 0.000 | 0.000 |
+| typo | rules | 0.1348 | 345 | 4 | 341 | 0.01 | 0.000 | 0.478 |
+| typo | model | 0.1348 | 347 | 5 | 342 | 0.01 | 0.000 | 0.492 |

edit-qwen3.5-2b/test_eval/metrics.json

@@ -0,0 +1,26 @@
+{
+  "n_examples": 1978,
+  "wer": 0.18625879345772253,
+  "wer_zwnj_normalized": 0.17447817680014543,
+  "exact_match": 0.006572295247724975,
+  "hallucination_rate": 0.0,
+  "rows_changed": 0.6941354903943378,
+  "fix_rate": 0.05573919446054548,
+  "preservation_rate": 0.9995655385150106,
+  "targeted_score": 0.527652366487778,
+  "fix_rate_lenient": 0.05907235256504845,
+  "preservation_rate_lenient": 0.9995470033941437,
+  "targeted_score_lenient": 0.529309677979596,
+  "fixed_lenient": 3603,
+  "broken_lenient": 136,
+  "net_fixed_lenient": 3467,
+  "broken_per_100_correct": 0.04529966058563135,
+  "fix_rate_recoverable": 0.05972312459393273,
+  "unrecoverable_targets": 966,
+  "entity_fix_rate": 0.017543859649122806,
+  "entity_keep_rate": 1.0,
+  "entity_spans_whisper_wrong": 57,
+  "entity_spans_whisper_right": 217,
+  "rejected_lines_per_transcript": 0.005055611729019211,
+  "edits_per_transcript": 0.020728008088978768
+}

edit-qwen3.5-2b/test_eval/predictions.jsonl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be41bd8608e6ce3a0d1f7c16065b93735bc05fc52a71cbf97a591d80a7beec88
+size 13064335

edit-qwen3.5-2b/test_eval_entity/baselines.json

@@ -0,0 +1,50 @@
+{
+  "whisper": {
+    "n_examples": 1010,
+    "wer": 0.18660667584675655,
+    "wer_zwnj_normalized": 0.17409613475517982,
+    "exact_match": 0.0049504950495049506,
+    "hallucination_rate": 0.0,
+    "rows_changed": 0.0,
+    "fix_rate": 0.0,
+    "preservation_rate": 1.0,
+    "targeted_score": 0.5,
+    "fix_rate_lenient": 0.0,
+    "preservation_rate_lenient": 1.0,
+    "targeted_score_lenient": 0.5,
+    "fixed_lenient": 0,
+    "broken_lenient": 0,
+    "net_fixed_lenient": 0,
+    "broken_per_100_correct": 0.0,
+    "fix_rate_recoverable": 0.0,
+    "unrecoverable_targets": 471,
+    "entity_fix_rate": 0.0,
+    "entity_keep_rate": 1.0,
+    "entity_spans_whisper_wrong": 57,
+    "entity_spans_whisper_right": 217
+  },
+  "rules": {
+    "n_examples": 1010,
+    "wer": 0.18000982056126644,
+    "wer_zwnj_normalized": 0.16776614254758168,
+    "exact_match": 0.0049504950495049506,
+    "hallucination_rate": 0.0,
+    "rows_changed": 0.7148514851485148,
+    "fix_rate": 0.0566740770892695,
+    "preservation_rate": 0.9996911693742963,
+    "targeted_score": 0.5281826232317829,
+    "fix_rate_lenient": 0.06019704433497537,
+    "preservation_rate_lenient": 0.9996856677315474,
+    "targeted_score_lenient": 0.5299413560332614,
+    "fixed_lenient": 1833,
+    "broken_lenient": 49,
+    "net_fixed_lenient": 1784,
+    "broken_per_100_correct": 0.03143322684525871,
+    "fix_rate_recoverable": 0.06077587644684613,
+    "unrecoverable_targets": 471,
+    "entity_fix_rate": 0.0,
+    "entity_keep_rate": 1.0,
+    "entity_spans_whisper_wrong": 57,
+    "entity_spans_whisper_right": 217
+  }
+}

edit-qwen3.5-2b/test_eval_entity/metrics.json

@@ -0,0 +1,26 @@
+{
+  "n_examples": 1010,
+  "wer": 0.1800311696074978,
+  "wer_zwnj_normalized": 0.16778749159381304,
+  "exact_match": 0.0049504950495049506,
+  "hallucination_rate": 0.0,
+  "rows_changed": 0.7227722772277227,
+  "fix_rate": 0.05683063531327301,
+  "preservation_rate": 0.9996332636319768,
+  "targeted_score": 0.5282319494726249,
+  "fix_rate_lenient": 0.060361247947454844,
+  "preservation_rate_lenient": 0.9996279332332602,
+  "targeted_score_lenient": 0.5299945905903575,
+  "fixed_lenient": 1838,
+  "broken_lenient": 58,
+  "net_fixed_lenient": 1780,
+  "broken_per_100_correct": 0.037206676673979706,
+  "fix_rate_recoverable": 0.06094265986190333,
+  "unrecoverable_targets": 471,
+  "entity_fix_rate": 0.017543859649122806,
+  "entity_keep_rate": 1.0,
+  "entity_spans_whisper_wrong": 57,
+  "entity_spans_whisper_right": 217,
+  "rejected_lines_per_transcript": 0.0049504950495049506,
+  "edits_per_transcript": 0.02277227722772277
+}

edit-qwen3.5-2b/test_eval_typo/baselines.json

@@ -0,0 +1,50 @@
+{
+  "whisper": {
+    "n_examples": 358,
+    "wer": 0.14117586990375533,
+    "wer_zwnj_normalized": 0.12749227745015446,
+    "exact_match": 0.0,
+    "hallucination_rate": 0.0,
+    "rows_changed": 0.0,
+    "fix_rate": 0.0,
+    "preservation_rate": 1.0,
+    "targeted_score": 0.5,
+    "fix_rate_lenient": 0.0,
+    "preservation_rate_lenient": 1.0,
+    "targeted_score_lenient": 0.5,
+    "fixed_lenient": 0,
+    "broken_lenient": 0,
+    "net_fixed_lenient": 0,
+    "broken_per_100_correct": 0.0,
+    "fix_rate_recoverable": 0.0,
+    "unrecoverable_targets": 68,
+    "entity_fix_rate": 0.0,
+    "entity_keep_rate": 1.0,
+    "entity_spans_whisper_wrong": 9,
+    "entity_spans_whisper_right": 61
+  },
+  "rules": {
+    "n_examples": 358,
+    "wer": 0.13481912639452656,
+    "wer_zwnj_normalized": 0.12139082484491077,
+    "exact_match": 0.002793296089385475,
+    "hallucination_rate": 0.0,
+    "rows_changed": 0.4776536312849162,
+    "fix_rate": 0.06630476929042264,
+    "preservation_rate": 0.9998823979066828,
+    "targeted_score": 0.5330935835985527,
+    "fix_rate_lenient": 0.07141378596563859,
+    "preservation_rate_lenient": 0.9998827976207917,
+    "targeted_score_lenient": 0.5356482917932152,
+    "fixed_lenient": 345,
+    "broken_lenient": 4,
+    "net_fixed_lenient": 341,
+    "broken_per_100_correct": 0.011720237920829792,
+    "fix_rate_recoverable": 0.07222338862061725,
+    "unrecoverable_targets": 68,
+    "entity_fix_rate": 0.0,
+    "entity_keep_rate": 1.0,
+    "entity_spans_whisper_wrong": 9,
+    "entity_spans_whisper_right": 61
+  }
+}

edit-qwen3.5-2b/test_eval_typo/metrics.json

@@ -0,0 +1,26 @@
+{
+  "n_examples": 358,
+  "wer": 0.13479359730412804,
+  "wer_zwnj_normalized": 0.12136529575451227,
+  "exact_match": 0.002793296089385475,
+  "hallucination_rate": 0.0,
+  "rows_changed": 0.49162011173184356,
+  "fix_rate": 0.06669251647925553,
+  "preservation_rate": 0.9998529973833534,
+  "targeted_score": 0.5332727569313045,
+  "fix_rate_lenient": 0.07182777892775823,
+  "preservation_rate_lenient": 0.9998534970259896,
+  "targeted_score_lenient": 0.5358406379768739,
+  "fixed_lenient": 347,
+  "broken_lenient": 5,
+  "net_fixed_lenient": 342,
+  "broken_per_100_correct": 0.014650297401037241,
+  "fix_rate_recoverable": 0.07264329204283015,
+  "unrecoverable_targets": 68,
+  "entity_fix_rate": 0.0,
+  "entity_keep_rate": 1.0,
+  "entity_spans_whisper_wrong": 9,
+  "entity_spans_whisper_right": 61,
+  "rejected_lines_per_transcript": 0.002793296089385475,
+  "edits_per_transcript": 0.01675977653631285
+}

edit-qwen3.5-2b/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06b9509352d2af50381ab2247e083b80d32d5c0aba91c272ca9ff729b6a0e523
+size 19989325

edit-qwen3.5-2b/tokenizer_config.json

@@ -0,0 +1,32 @@
+{
+  "add_prefix_space": false,
+  "audio_bos_token": "<|audio_start|>",
+  "audio_eos_token": "<|audio_end|>",
+  "audio_token": "<|audio_pad|>",
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "image_token": "<|image_pad|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 262144,
+  "model_specific_special_tokens": {
+    "audio_bos_token": "<|audio_start|>",
+    "audio_eos_token": "<|audio_end|>",
+    "audio_token": "<|audio_pad|>",
+    "image_token": "<|image_pad|>",
+    "video_token": "<|video_pad|>",
+    "vision_bos_token": "<|vision_start|>",
+    "vision_eos_token": "<|vision_end|>"
+  },
+  "pad_token": "<|endoftext|>",
+  "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "video_token": "<|video_pad|>",
+  "vision_bos_token": "<|vision_start|>",
+  "vision_eos_token": "<|vision_end|>"
+}

edit-qwen3.5-2b/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33972d7442254fc5f6c1267830686f8be8e133c4a96736fbf8eb7e1ef4f9bd29
+size 5265

edit-qwen3.5-2b/validation_edits.json

@@ -0,0 +1,9 @@
+{
+  "windows": 144,
+  "edit_precision": 0.0,
+  "edit_recall": 0.0,
+  "window_exact_match": 0.5555555555555556,
+  "rejected_lines": 1,
+  "predicted_edits": 2,
+  "gold_edits": 96
+}