Migrated Qwen3-ASR-0.6B/E2_Noise to root
Browse files- .gitattributes +1 -0
- README.md +69 -0
- added_tokens.json +64 -0
- chat_template.jinja +31 -0
- config.json +224 -0
- generation_config.json +8 -0
- logs/tensorboard/events.out.tfevents.1780855414.AESPANINGNING.42513.0 +3 -0
- merges.txt +0 -0
- metrics/prediction.csv +0 -0
- metrics/result.json +20 -0
- metrics/summary.json +26 -0
- metrics/training_logs.csv +44 -0
- model.safetensors +3 -0
- preprocessor_config.json +15 -0
- special_tokens_map.json +44 -0
- tokenizer.json +3 -0
- tokenizer_config.json +550 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ 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 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- lus
|
| 4 |
+
license: apache-2.0
|
| 5 |
+
base_model: Qwen/Qwen2-Audio-7B
|
| 6 |
+
tags:
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
datasets:
|
| 9 |
+
- andrewbawitlung/mizonal-v3
|
| 10 |
+
metrics:
|
| 11 |
+
- wer
|
| 12 |
+
model-index:
|
| 13 |
+
- name: qwen3-asr-0.6b-mizonal3-E2-lus-v2026.06
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
name: Automatic Speech Recognition
|
| 17 |
+
type: automatic-speech-recognition
|
| 18 |
+
dataset:
|
| 19 |
+
name: MiZonal v3
|
| 20 |
+
type: andrewbawitlung/mizonal-v3
|
| 21 |
+
config: default
|
| 22 |
+
split: test
|
| 23 |
+
metrics:
|
| 24 |
+
- name: Wer
|
| 25 |
+
type: wer
|
| 26 |
+
value: 19.4954
|
| 27 |
+
---
|
| 28 |
+
|
| 29 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 30 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 31 |
+
|
| 32 |
+
# qwen3-asr-0.6b-mizonal3-E2-lus-v2026.06
|
| 33 |
+
|
| 34 |
+
This model is a fine-tuned version of [Qwen/Qwen2-Audio-7B](https://huggingface.co/Qwen/Qwen2-Audio-7B) on the **MiZonal v3** dataset.
|
| 35 |
+
Note: ~1 hour of conversational speech was added to this dataset version.
|
| 36 |
+
|
| 37 |
+
It achieves the following results on the evaluation set:
|
| 38 |
+
- Wer: 19.4954
|
| 39 |
+
|
| 40 |
+
## Model description
|
| 41 |
+
|
| 42 |
+
### Experiment Configurations
|
| 43 |
+
This repository is part of a series of experiments. The different configurations are:
|
| 44 |
+
- **E1 (Baseline):** Standard training configuration.
|
| 45 |
+
- **E2 (Noise):** Training with background noise augmentation.
|
| 46 |
+
- **E3 (Speed):** Training with speed perturbation augmentation.
|
| 47 |
+
- **E4 (SpecAug):** Training with SpecAugment (time and frequency masking).
|
| 48 |
+
- **E5 (Combined):** Training with a combination of all augmentations.
|
| 49 |
+
|
| 50 |
+
### All Models in this Family
|
| 51 |
+
| Experiment | Hugging Face Repository |
|
| 52 |
+
| :--- | :--- |
|
| 53 |
+
| **E1 (Baseline)** | [andrewbawitlung/qwen3-asr-0.6b-mizonal3-E1-lus-v2026.06](https://huggingface.co/andrewbawitlung/qwen3-asr-0.6b-mizonal3-E1-lus-v2026.06) |
|
| 54 |
+
| **E2 (Noise)** | [andrewbawitlung/qwen3-asr-0.6b-mizonal3-E2-lus-v2026.06](https://huggingface.co/andrewbawitlung/qwen3-asr-0.6b-mizonal3-E2-lus-v2026.06) |
|
| 55 |
+
| **E3 (Speed)** | [andrewbawitlung/qwen3-asr-0.6b-mizonal3-E3-lus-v2026.06](https://huggingface.co/andrewbawitlung/qwen3-asr-0.6b-mizonal3-E3-lus-v2026.06) |
|
| 56 |
+
| **E4 (SpecAug)** | [andrewbawitlung/qwen3-asr-0.6b-mizonal3-E4-lus-v2026.06](https://huggingface.co/andrewbawitlung/qwen3-asr-0.6b-mizonal3-E4-lus-v2026.06) |
|
| 57 |
+
| **E5 (Combined)** | [andrewbawitlung/qwen3-asr-0.6b-mizonal3-E5-lus-v2026.06](https://huggingface.co/andrewbawitlung/qwen3-asr-0.6b-mizonal3-E5-lus-v2026.06) |
|
| 58 |
+
|
| 59 |
+
## Intended uses & limitations
|
| 60 |
+
|
| 61 |
+
More information needed
|
| 62 |
+
|
| 63 |
+
## Training and evaluation data
|
| 64 |
+
|
| 65 |
+
More information needed
|
| 66 |
+
|
| 67 |
+
## Training procedure
|
| 68 |
+
|
| 69 |
+
More information needed
|
added_tokens.json
ADDED
|
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<asr_text>": 151704,
|
| 6 |
+
"<blank10>": 151686,
|
| 7 |
+
"<blank11>": 151687,
|
| 8 |
+
"<blank12>": 151688,
|
| 9 |
+
"<blank13>": 151689,
|
| 10 |
+
"<blank14>": 151690,
|
| 11 |
+
"<blank15>": 151691,
|
| 12 |
+
"<blank16>": 151692,
|
| 13 |
+
"<blank17>": 151693,
|
| 14 |
+
"<blank18>": 151694,
|
| 15 |
+
"<blank19>": 151695,
|
| 16 |
+
"<blank1>": 151677,
|
| 17 |
+
"<blank20>": 151696,
|
| 18 |
+
"<blank21>": 151697,
|
| 19 |
+
"<blank22>": 151698,
|
| 20 |
+
"<blank23>": 151699,
|
| 21 |
+
"<blank24>": 151700,
|
| 22 |
+
"<blank25>": 151701,
|
| 23 |
+
"<blank26>": 151702,
|
| 24 |
+
"<blank27>": 151703,
|
| 25 |
+
"<blank2>": 151678,
|
| 26 |
+
"<blank3>": 151679,
|
| 27 |
+
"<blank4>": 151680,
|
| 28 |
+
"<blank5>": 151681,
|
| 29 |
+
"<blank6>": 151682,
|
| 30 |
+
"<blank7>": 151683,
|
| 31 |
+
"<blank8>": 151684,
|
| 32 |
+
"<blank9>": 151685,
|
| 33 |
+
"<non_speech>": 151675,
|
| 34 |
+
"<think>": 151667,
|
| 35 |
+
"<tool_call>": 151657,
|
| 36 |
+
"<tool_response>": 151665,
|
| 37 |
+
"<tts_pad>": 151671,
|
| 38 |
+
"<tts_text_bos>": 151672,
|
| 39 |
+
"<tts_text_bos_single>": 151674,
|
| 40 |
+
"<tts_text_eod>": 151673,
|
| 41 |
+
"<|audio_end|>": 151670,
|
| 42 |
+
"<|audio_pad|>": 151676,
|
| 43 |
+
"<|audio_start|>": 151669,
|
| 44 |
+
"<|box_end|>": 151649,
|
| 45 |
+
"<|box_start|>": 151648,
|
| 46 |
+
"<|endoftext|>": 151643,
|
| 47 |
+
"<|file_sep|>": 151664,
|
| 48 |
+
"<|fim_middle|>": 151660,
|
| 49 |
+
"<|fim_pad|>": 151662,
|
| 50 |
+
"<|fim_prefix|>": 151659,
|
| 51 |
+
"<|fim_suffix|>": 151661,
|
| 52 |
+
"<|im_end|>": 151645,
|
| 53 |
+
"<|im_start|>": 151644,
|
| 54 |
+
"<|image_pad|>": 151655,
|
| 55 |
+
"<|object_ref_end|>": 151647,
|
| 56 |
+
"<|object_ref_start|>": 151646,
|
| 57 |
+
"<|quad_end|>": 151651,
|
| 58 |
+
"<|quad_start|>": 151650,
|
| 59 |
+
"<|repo_name|>": 151663,
|
| 60 |
+
"<|video_pad|>": 151656,
|
| 61 |
+
"<|vision_end|>": 151653,
|
| 62 |
+
"<|vision_pad|>": 151654,
|
| 63 |
+
"<|vision_start|>": 151652
|
| 64 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set ns = namespace(system_text="") -%}
|
| 2 |
+
{%- for m in messages -%}
|
| 3 |
+
{%- if m.role == 'system' -%}
|
| 4 |
+
{%- if m.content is string -%}
|
| 5 |
+
{%- set ns.system_text = ns.system_text + m.content -%}
|
| 6 |
+
{%- else -%}
|
| 7 |
+
{%- for c in m.content -%}
|
| 8 |
+
{%- if c.type == 'text' and (c.text is defined) -%}
|
| 9 |
+
{%- set ns.system_text = ns.system_text + c.text -%}
|
| 10 |
+
{%- endif -%}
|
| 11 |
+
{%- endfor -%}
|
| 12 |
+
{%- endif -%}
|
| 13 |
+
{%- endif -%}
|
| 14 |
+
{%- endfor -%}
|
| 15 |
+
|
| 16 |
+
{%- set ns2 = namespace(audio_tokens="") -%}
|
| 17 |
+
{%- for m in messages -%}
|
| 18 |
+
{%- if m.content is not string -%}
|
| 19 |
+
{%- for c in m.content -%}
|
| 20 |
+
{%- if c.type == 'audio' or ('audio' in c) or ('audio_url' in c) -%}
|
| 21 |
+
{%- set ns2.audio_tokens = ns2.audio_tokens + "<|audio_start|><|audio_pad|><|audio_end|>" -%}
|
| 22 |
+
{%- endif -%}
|
| 23 |
+
{%- endfor -%}
|
| 24 |
+
{%- endif -%}
|
| 25 |
+
{%- endfor -%}
|
| 26 |
+
|
| 27 |
+
{{- '<|im_start|>system\n' + (ns.system_text if ns.system_text is string else '') + '<|im_end|>\n' -}}
|
| 28 |
+
{{- '<|im_start|>user\n' + ns2.audio_tokens + '<|im_end|>\n' -}}
|
| 29 |
+
{%- if add_generation_prompt -%}
|
| 30 |
+
{{- '<|im_start|>assistant\n' -}}
|
| 31 |
+
{%- endif -%}
|
config.json
ADDED
|
@@ -0,0 +1,224 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ASRForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"model_type": "qwen3_asr",
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"support_languages": [
|
| 10 |
+
"Chinese",
|
| 11 |
+
"English",
|
| 12 |
+
"Cantonese",
|
| 13 |
+
"Arabic",
|
| 14 |
+
"German",
|
| 15 |
+
"French",
|
| 16 |
+
"Spanish",
|
| 17 |
+
"Portuguese",
|
| 18 |
+
"Indonesian",
|
| 19 |
+
"Italian",
|
| 20 |
+
"Korean",
|
| 21 |
+
"Russian",
|
| 22 |
+
"Thai",
|
| 23 |
+
"Vietnamese",
|
| 24 |
+
"Japanese",
|
| 25 |
+
"Turkish",
|
| 26 |
+
"Hindi",
|
| 27 |
+
"Malay",
|
| 28 |
+
"Dutch",
|
| 29 |
+
"Swedish",
|
| 30 |
+
"Danish",
|
| 31 |
+
"Finnish",
|
| 32 |
+
"Polish",
|
| 33 |
+
"Czech",
|
| 34 |
+
"Filipino",
|
| 35 |
+
"Persian",
|
| 36 |
+
"Greek",
|
| 37 |
+
"Romanian",
|
| 38 |
+
"Hungarian",
|
| 39 |
+
"Macedonian"
|
| 40 |
+
],
|
| 41 |
+
"thinker_config": {
|
| 42 |
+
"architectures": [
|
| 43 |
+
"Qwen3ASRForConditionalGeneration"
|
| 44 |
+
],
|
| 45 |
+
"audio_config": {
|
| 46 |
+
"_name_or_path": "",
|
| 47 |
+
"activation_dropout": 0,
|
| 48 |
+
"activation_function": "gelu",
|
| 49 |
+
"add_cross_attention": false,
|
| 50 |
+
"architectures": null,
|
| 51 |
+
"attention_dropout": 0,
|
| 52 |
+
"bad_words_ids": null,
|
| 53 |
+
"begin_suppress_tokens": null,
|
| 54 |
+
"bos_token_id": null,
|
| 55 |
+
"chunk_size_feed_forward": 0,
|
| 56 |
+
"conv_chunksize": 500,
|
| 57 |
+
"cross_attention_hidden_size": null,
|
| 58 |
+
"d_model": 896,
|
| 59 |
+
"decoder_start_token_id": null,
|
| 60 |
+
"diversity_penalty": 0.0,
|
| 61 |
+
"do_sample": false,
|
| 62 |
+
"downsample_hidden_size": 480,
|
| 63 |
+
"dropout": 0,
|
| 64 |
+
"dtype": null,
|
| 65 |
+
"early_stopping": false,
|
| 66 |
+
"encoder_attention_heads": 14,
|
| 67 |
+
"encoder_ffn_dim": 3584,
|
| 68 |
+
"encoder_layers": 18,
|
| 69 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 70 |
+
"eos_token_id": null,
|
| 71 |
+
"exponential_decay_length_penalty": null,
|
| 72 |
+
"finetuning_task": null,
|
| 73 |
+
"forced_bos_token_id": null,
|
| 74 |
+
"forced_eos_token_id": null,
|
| 75 |
+
"id2label": {
|
| 76 |
+
"0": "LABEL_0",
|
| 77 |
+
"1": "LABEL_1"
|
| 78 |
+
},
|
| 79 |
+
"initializer_range": 0.02,
|
| 80 |
+
"is_decoder": false,
|
| 81 |
+
"is_encoder_decoder": false,
|
| 82 |
+
"label2id": {
|
| 83 |
+
"LABEL_0": 0,
|
| 84 |
+
"LABEL_1": 1
|
| 85 |
+
},
|
| 86 |
+
"length_penalty": 1.0,
|
| 87 |
+
"max_length": 20,
|
| 88 |
+
"max_source_positions": 1500,
|
| 89 |
+
"min_length": 0,
|
| 90 |
+
"model_type": "qwen3_asr_audio_encoder",
|
| 91 |
+
"n_window": 50,
|
| 92 |
+
"n_window_infer": 800,
|
| 93 |
+
"no_repeat_ngram_size": 0,
|
| 94 |
+
"num_beam_groups": 1,
|
| 95 |
+
"num_beams": 1,
|
| 96 |
+
"num_hidden_layers": 18,
|
| 97 |
+
"num_mel_bins": 128,
|
| 98 |
+
"num_return_sequences": 1,
|
| 99 |
+
"output_attentions": false,
|
| 100 |
+
"output_dim": 1024,
|
| 101 |
+
"output_hidden_states": false,
|
| 102 |
+
"output_scores": false,
|
| 103 |
+
"pad_token_id": null,
|
| 104 |
+
"prefix": null,
|
| 105 |
+
"problem_type": null,
|
| 106 |
+
"pruned_heads": {},
|
| 107 |
+
"remove_invalid_values": false,
|
| 108 |
+
"repetition_penalty": 1.0,
|
| 109 |
+
"return_dict": true,
|
| 110 |
+
"return_dict_in_generate": false,
|
| 111 |
+
"scale_embedding": false,
|
| 112 |
+
"sep_token_id": null,
|
| 113 |
+
"suppress_tokens": null,
|
| 114 |
+
"task_specific_params": null,
|
| 115 |
+
"temperature": 1.0,
|
| 116 |
+
"tf_legacy_loss": false,
|
| 117 |
+
"tie_encoder_decoder": false,
|
| 118 |
+
"tie_word_embeddings": true,
|
| 119 |
+
"tokenizer_class": null,
|
| 120 |
+
"top_k": 50,
|
| 121 |
+
"top_p": 1.0,
|
| 122 |
+
"torchscript": false,
|
| 123 |
+
"typical_p": 1.0,
|
| 124 |
+
"use_bfloat16": false
|
| 125 |
+
},
|
| 126 |
+
"audio_end_token_id": 151670,
|
| 127 |
+
"audio_start_token_id": 151669,
|
| 128 |
+
"audio_token_id": 151676,
|
| 129 |
+
"dtype": "bfloat16",
|
| 130 |
+
"initializer_range": 0.02,
|
| 131 |
+
"model_type": "qwen3_asr_thinker",
|
| 132 |
+
"text_config": {
|
| 133 |
+
"_name_or_path": "",
|
| 134 |
+
"add_cross_attention": false,
|
| 135 |
+
"architectures": null,
|
| 136 |
+
"attention_bias": false,
|
| 137 |
+
"attention_dropout": 0.0,
|
| 138 |
+
"bad_words_ids": null,
|
| 139 |
+
"begin_suppress_tokens": null,
|
| 140 |
+
"bos_token_id": null,
|
| 141 |
+
"chunk_size_feed_forward": 0,
|
| 142 |
+
"cross_attention_hidden_size": null,
|
| 143 |
+
"decoder_start_token_id": null,
|
| 144 |
+
"diversity_penalty": 0.0,
|
| 145 |
+
"do_sample": false,
|
| 146 |
+
"dtype": null,
|
| 147 |
+
"early_stopping": false,
|
| 148 |
+
"encoder_no_repeat_ngram_size": 0,
|
| 149 |
+
"eos_token_id": null,
|
| 150 |
+
"exponential_decay_length_penalty": null,
|
| 151 |
+
"finetuning_task": null,
|
| 152 |
+
"forced_bos_token_id": null,
|
| 153 |
+
"forced_eos_token_id": null,
|
| 154 |
+
"head_dim": 128,
|
| 155 |
+
"hidden_act": "silu",
|
| 156 |
+
"hidden_size": 1024,
|
| 157 |
+
"id2label": {
|
| 158 |
+
"0": "LABEL_0",
|
| 159 |
+
"1": "LABEL_1"
|
| 160 |
+
},
|
| 161 |
+
"initializer_range": 0.02,
|
| 162 |
+
"intermediate_size": 3072,
|
| 163 |
+
"is_decoder": false,
|
| 164 |
+
"is_encoder_decoder": false,
|
| 165 |
+
"label2id": {
|
| 166 |
+
"LABEL_0": 0,
|
| 167 |
+
"LABEL_1": 1
|
| 168 |
+
},
|
| 169 |
+
"length_penalty": 1.0,
|
| 170 |
+
"max_length": 20,
|
| 171 |
+
"max_position_embeddings": 65536,
|
| 172 |
+
"min_length": 0,
|
| 173 |
+
"model_type": "qwen3_asr_text",
|
| 174 |
+
"no_repeat_ngram_size": 0,
|
| 175 |
+
"num_attention_heads": 16,
|
| 176 |
+
"num_beam_groups": 1,
|
| 177 |
+
"num_beams": 1,
|
| 178 |
+
"num_hidden_layers": 28,
|
| 179 |
+
"num_key_value_heads": 8,
|
| 180 |
+
"num_return_sequences": 1,
|
| 181 |
+
"output_attentions": false,
|
| 182 |
+
"output_hidden_states": false,
|
| 183 |
+
"output_scores": false,
|
| 184 |
+
"pad_token_id": null,
|
| 185 |
+
"prefix": null,
|
| 186 |
+
"problem_type": null,
|
| 187 |
+
"pruned_heads": {},
|
| 188 |
+
"remove_invalid_values": false,
|
| 189 |
+
"repetition_penalty": 1.0,
|
| 190 |
+
"return_dict": true,
|
| 191 |
+
"return_dict_in_generate": false,
|
| 192 |
+
"rms_norm_eps": 1e-06,
|
| 193 |
+
"rope_scaling": {
|
| 194 |
+
"interleaved": true,
|
| 195 |
+
"mrope_interleaved": true,
|
| 196 |
+
"mrope_section": [
|
| 197 |
+
24,
|
| 198 |
+
20,
|
| 199 |
+
20
|
| 200 |
+
],
|
| 201 |
+
"rope_type": "default",
|
| 202 |
+
"type": "default"
|
| 203 |
+
},
|
| 204 |
+
"rope_theta": 1000000,
|
| 205 |
+
"sep_token_id": null,
|
| 206 |
+
"suppress_tokens": null,
|
| 207 |
+
"task_specific_params": null,
|
| 208 |
+
"temperature": 1.0,
|
| 209 |
+
"tf_legacy_loss": false,
|
| 210 |
+
"tie_encoder_decoder": false,
|
| 211 |
+
"tie_word_embeddings": true,
|
| 212 |
+
"tokenizer_class": null,
|
| 213 |
+
"top_k": 50,
|
| 214 |
+
"top_p": 1.0,
|
| 215 |
+
"torchscript": false,
|
| 216 |
+
"typical_p": 1.0,
|
| 217 |
+
"use_bfloat16": false,
|
| 218 |
+
"use_cache": true,
|
| 219 |
+
"vocab_size": 151936
|
| 220 |
+
},
|
| 221 |
+
"user_token_id": 872
|
| 222 |
+
},
|
| 223 |
+
"transformers_version": "4.57.6"
|
| 224 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645
|
| 5 |
+
],
|
| 6 |
+
"pad_token_id": 151643,
|
| 7 |
+
"transformers_version": "4.57.6"
|
| 8 |
+
}
|
logs/tensorboard/events.out.tfevents.1780855414.AESPANINGNING.42513.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54fb41b1b2afa7f2354bcfc4b024889fac1c3dfb7b0ea9601e20b6e27e501136
|
| 3 |
+
size 213824
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
metrics/prediction.csv
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
metrics/result.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"experiment": "E2_Noise",
|
| 3 |
+
"split": "test",
|
| 4 |
+
"model": "test_eval_temp",
|
| 5 |
+
"model_hf_name": "/home/workstation/workspace/Afaka/Code/Qwen3-ASR-Fine-Tuning/outputs/Qwen3-ASR-0.6B/E2_Noise/final_model",
|
| 6 |
+
"seed": 42,
|
| 7 |
+
"smoke_test": false,
|
| 8 |
+
"training_time_sec": 0.0,
|
| 9 |
+
"training_loss": 0.0,
|
| 10 |
+
"test_wer": 0.194954,
|
| 11 |
+
"test_cer": 0.044174,
|
| 12 |
+
"test_ter": 0.0,
|
| 13 |
+
"test_rtf": 0.065952,
|
| 14 |
+
"gpu_name": "NVIDIA RTX 4500 Ada Generation",
|
| 15 |
+
"gpu_total_memory_gb": 24.0,
|
| 16 |
+
"gpu_peak_memory_mb": 6166.2,
|
| 17 |
+
"timestamp": "2026-06-07T22:25:56.883330",
|
| 18 |
+
"manifest_path": "/home/workstation/workspace/Afaka/Code/Qwen3-ASR-Fine-Tuning/data/manifests/E2_Noise/mizo_test.jsonl",
|
| 19 |
+
"predictions_path": "/home/workstation/workspace/Afaka/Code/Qwen3-ASR-Fine-Tuning/outputs/Qwen3-ASR-0.6B/E2_Noise/evaluation/prediction.csv"
|
| 20 |
+
}
|
metrics/summary.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_path": "/home/workstation/workspace/Afaka/Code/Qwen3-ASR-Fine-Tuning/outputs/Qwen3-ASR-0.6B/E2_Noise/final_model",
|
| 3 |
+
"output_dir": "/home/workstation/workspace/Afaka/Code/Qwen3-ASR-Fine-Tuning/outputs/Qwen3-ASR-0.6B/E2_Noise",
|
| 4 |
+
"seed": 42,
|
| 5 |
+
"smoke_test": false,
|
| 6 |
+
"evaluation": {
|
| 7 |
+
"experiment": "E2_Noise",
|
| 8 |
+
"split": "test",
|
| 9 |
+
"model": "test_eval_temp",
|
| 10 |
+
"model_hf_name": "/home/workstation/workspace/Afaka/Code/Qwen3-ASR-Fine-Tuning/outputs/Qwen3-ASR-0.6B/E2_Noise/final_model",
|
| 11 |
+
"seed": 42,
|
| 12 |
+
"smoke_test": false,
|
| 13 |
+
"training_time_sec": 0.0,
|
| 14 |
+
"training_loss": 0.0,
|
| 15 |
+
"test_wer": 0.194954,
|
| 16 |
+
"test_cer": 0.044174,
|
| 17 |
+
"test_ter": 0.0,
|
| 18 |
+
"test_rtf": 0.065952,
|
| 19 |
+
"gpu_name": "NVIDIA RTX 4500 Ada Generation",
|
| 20 |
+
"gpu_total_memory_gb": 24.0,
|
| 21 |
+
"gpu_peak_memory_mb": 6166.2,
|
| 22 |
+
"timestamp": "2026-06-07T22:25:56.883330",
|
| 23 |
+
"manifest_path": "/home/workstation/workspace/Afaka/Code/Qwen3-ASR-Fine-Tuning/data/manifests/E2_Noise/mizo_test.jsonl",
|
| 24 |
+
"predictions_path": "/home/workstation/workspace/Afaka/Code/Qwen3-ASR-Fine-Tuning/outputs/Qwen3-ASR-0.6B/E2_Noise/evaluation/prediction.csv"
|
| 25 |
+
}
|
| 26 |
+
}
|
metrics/training_logs.csv
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
step,epoch,train_loss,eval_loss,eval_wer,eval_cer,learning_rate,grad_norm
|
| 2 |
+
200,0.18214936247723132,0.4524,0.7468264102935791,0.5282670039894911,0.1620900480633305,1.9946561338289966e-05,14.5
|
| 3 |
+
400,0.36429872495446264,0.2727,0.40020251274108887,0.322467646200253,0.0809301668080294,1.9481877323420074e-05,10.8125
|
| 4 |
+
600,0.546448087431694,0.1697,0.3364563286304474,0.27955629074632676,0.06432004523607578,1.9017193308550188e-05,7.5625
|
| 5 |
+
800,0.7285974499089253,0.2061,0.29908183217048645,0.24871071324316435,0.059849448685326545,1.85525092936803e-05,5.78125
|
| 6 |
+
1000,0.9107468123861566,0.1388,0.2859058380126953,0.24404008952028802,0.05465436810856658,1.808782527881041e-05,7.375
|
| 7 |
+
1200,1.092896174863388,0.0883,0.2675563097000122,0.22506568064610294,0.052604608425219114,1.762314126394052e-05,5.65625
|
| 8 |
+
1400,1.2750455373406193,0.0722,0.26070064306259155,0.2159190425221368,0.05103194797851286,1.7158457249070632e-05,3.84375
|
| 9 |
+
1600,1.4571948998178508,0.0763,0.2592693865299225,0.21309720735623236,0.04882315521628499,1.6693773234200746e-05,4.4375
|
| 10 |
+
1800,1.639344262295082,0.0755,0.252381831407547,0.20035029677921573,0.04634930732258977,1.6229089219330857e-05,8.8125
|
| 11 |
+
2000,1.8214936247723132,0.0622,0.24645309150218964,0.20229638999708086,0.04539510884930732,1.5764405204460968e-05,4.59375
|
| 12 |
+
2200,2.0036429872495445,0.0477,0.24331779778003693,0.19957185949206968,0.045342097823013856,1.529972118959108e-05,3.84375
|
| 13 |
+
2400,2.185792349726776,0.0447,0.25787490606307983,0.20180986669261458,0.046773395532937516,1.4835037174721192e-05,5.65625
|
| 14 |
+
2600,2.3679417122040074,0.0332,0.25755423307418823,0.19314975187311473,0.045077042691546505,1.4370353159851303e-05,3.4375
|
| 15 |
+
2800,2.5500910746812386,0.0305,0.2666151821613312,0.19383088449936753,0.04451159174441617,1.3905669144981413e-05,7.21875
|
| 16 |
+
3000,2.73224043715847,0.0297,0.2642105221748352,0.19752846161331128,0.047179813401187445,1.3440985130111526e-05,4.21875
|
| 17 |
+
3200,2.9143897996357016,0.0472,0.2631722390651703,0.18964678408095748,0.04343370087644897,1.2976301115241637e-05,4.34375
|
| 18 |
+
3400,3.096539162112933,0.0152,0.28036123514175415,0.19305244721222148,0.043857789086796724,1.251161710037175e-05,4.46875
|
| 19 |
+
3600,3.278688524590164,0.0114,0.2897799611091614,0.19285783789043495,0.04419352558665536,1.2046933085501859e-05,2.515625
|
| 20 |
+
3800,3.4608378870673953,0.0159,0.2936338484287262,0.18770069086309235,0.043769437376307604,1.158224907063197e-05,2.9375
|
| 21 |
+
4000,3.6429872495446265,0.009,0.2900753617286682,0.1934416658557945,0.04410517387616624,1.1117565055762082e-05,2.0625
|
| 22 |
+
4200,3.8251366120218577,0.0115,0.2965144217014313,0.19110635399435633,0.04484732824427481,1.0652881040892193e-05,4.1875
|
| 23 |
+
4400,4.007285974499089,0.0062,0.3001888692378998,0.18828451882845187,0.043363019508057675,1.0188197026022306e-05,5.15625
|
| 24 |
+
4600,4.18943533697632,0.0054,0.3130307197570801,0.18604651162790697,0.04290359061351428,9.723513011152417e-06,1.2265625
|
| 25 |
+
4800,4.371584699453552,0.0047,0.31496503949165344,0.1905225260289968,0.044158184902459714,9.258828996282528e-06,1.2109375
|
| 26 |
+
5000,4.553734061930784,0.0094,0.3163476586341858,0.1927605332295417,0.044564602770709644,8.79414498141264e-06,0.9375
|
| 27 |
+
5200,4.735883424408015,0.0037,0.3209853768348694,0.19013330738542375,0.04429954763924229,8.329460966542751e-06,1.0546875
|
| 28 |
+
5400,4.918032786885246,0.0041,0.3182981014251709,0.19042522136810353,0.04378710771840543,7.864776951672864e-06,0.9921875
|
| 29 |
+
5600,5.100182149362477,0.0022,0.33114519715309143,0.19353897051668775,0.04442324003392706,7.400092936802975e-06,0.4609375
|
| 30 |
+
5800,5.2823315118397085,0.0022,0.33354538679122925,0.19169018195971588,0.04440556969182923,6.935408921933086e-06,0.703125
|
| 31 |
+
6000,5.46448087431694,0.0023,0.33456122875213623,0.18993869806363725,0.04373409669211196,6.4707249070631975e-06,0.84375
|
| 32 |
+
6200,5.646630236794171,0.0027,0.3360964357852936,0.1927605332295417,0.044175855244557534,6.006040892193309e-06,0.59765625
|
| 33 |
+
6400,5.828779599271402,0.0025,0.33629176020622253,0.1927605332295417,0.044864998586372634,5.54135687732342e-06,2.15625
|
| 34 |
+
6600,6.0109289617486334,0.0019,0.3365257680416107,0.19042522136810353,0.04419352558665536,5.076672862453532e-06,0.45703125
|
| 35 |
+
6800,6.193078324225866,0.0022,0.34069618582725525,0.19266322856864843,0.04421119592875318,4.611988847583643e-06,0.349609375
|
| 36 |
+
7000,6.375227686703097,0.0018,0.3427211046218872,0.19353897051668775,0.04472363584959005,4.147304832713755e-06,0.380859375
|
| 37 |
+
7200,6.557377049180328,0.0018,0.3420465290546417,0.19169018195971588,0.044529262086514,3.6826208178438664e-06,0.61328125
|
| 38 |
+
7400,6.739526411657559,0.0034,0.34137850999832153,0.19305244721222148,0.04449392140231835,3.217936802973978e-06,0.4140625
|
| 39 |
+
7600,6.9216757741347905,0.0019,0.34198904037475586,0.19149557263792935,0.04382244840260108,2.7532527881040896e-06,0.3515625
|
| 40 |
+
7800,7.103825136612022,0.0017,0.34269949793815613,0.19266322856864843,0.044175855244557534,2.288568773234201e-06,0.4296875
|
| 41 |
+
8000,7.285974499089253,0.0024,0.34260717034339905,0.19460932178651358,0.0449180096126661,1.8238847583643125e-06,0.51953125
|
| 42 |
+
8200,7.468123861566484,0.0016,0.34319037199020386,0.19314975187311473,0.044882668928470454,1.3592007434944238e-06,0.279296875
|
| 43 |
+
8400,7.6502732240437155,0.0017,0.3434956669807434,0.19237131458596868,0.04431721798134012,8.945167286245354e-07,0.326171875
|
| 44 |
+
8600,7.832422586520947,0.0021,0.342936247587204,0.193636275177581,0.04449392140231835,4.298327137546469e-07,0.73828125
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:662090cd61c41da6dc91eb9789acac83d579164132ee584aac0e504e2333f7a3
|
| 3 |
+
size 1564926456
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,15 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"dither": 0.0,
|
| 4 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 5 |
+
"feature_size": 128,
|
| 6 |
+
"hop_length": 160,
|
| 7 |
+
"n_fft": 400,
|
| 8 |
+
"n_samples": 480000,
|
| 9 |
+
"nb_max_frames": 3000,
|
| 10 |
+
"padding_side": "right",
|
| 11 |
+
"padding_value": 0.0,
|
| 12 |
+
"processor_class": "Qwen3ASRProcessor",
|
| 13 |
+
"return_attention_mask": true,
|
| 14 |
+
"sampling_rate": 16000
|
| 15 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>",
|
| 16 |
+
"<|audio_start|>",
|
| 17 |
+
"<|audio_end|>",
|
| 18 |
+
"<tts_pad>",
|
| 19 |
+
"<tts_text_bos>",
|
| 20 |
+
"<tts_text_bos_single>",
|
| 21 |
+
"<|audio_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"audio_bos_token": "<|audio_start|>",
|
| 24 |
+
"audio_eos_token": "<|audio_end|>",
|
| 25 |
+
"audio_token": "<|audio_pad|>",
|
| 26 |
+
"eos_token": {
|
| 27 |
+
"content": "<|im_end|>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"image_token": "<|image_pad|>",
|
| 34 |
+
"pad_token": {
|
| 35 |
+
"content": "<|endoftext|>",
|
| 36 |
+
"lstrip": false,
|
| 37 |
+
"normalized": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"single_word": false
|
| 40 |
+
},
|
| 41 |
+
"video_token": "<|video_pad|>",
|
| 42 |
+
"vision_bos_token": "<|vision_start|>",
|
| 43 |
+
"vision_eos_token": "<|vision_end|>"
|
| 44 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:63f8e35e911612f1266ae056e69efc7eebeed90a3517fd3ca08937ce1c0e5e43
|
| 3 |
+
size 11429544
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,550 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
},
|
| 213 |
+
"151669": {
|
| 214 |
+
"content": "<|audio_start|>",
|
| 215 |
+
"lstrip": false,
|
| 216 |
+
"normalized": false,
|
| 217 |
+
"rstrip": false,
|
| 218 |
+
"single_word": false,
|
| 219 |
+
"special": true
|
| 220 |
+
},
|
| 221 |
+
"151670": {
|
| 222 |
+
"content": "<|audio_end|>",
|
| 223 |
+
"lstrip": false,
|
| 224 |
+
"normalized": false,
|
| 225 |
+
"rstrip": false,
|
| 226 |
+
"single_word": false,
|
| 227 |
+
"special": true
|
| 228 |
+
},
|
| 229 |
+
"151671": {
|
| 230 |
+
"content": "<tts_pad>",
|
| 231 |
+
"lstrip": false,
|
| 232 |
+
"normalized": false,
|
| 233 |
+
"rstrip": false,
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"special": true
|
| 236 |
+
},
|
| 237 |
+
"151672": {
|
| 238 |
+
"content": "<tts_text_bos>",
|
| 239 |
+
"lstrip": false,
|
| 240 |
+
"normalized": false,
|
| 241 |
+
"rstrip": false,
|
| 242 |
+
"single_word": false,
|
| 243 |
+
"special": true
|
| 244 |
+
},
|
| 245 |
+
"151673": {
|
| 246 |
+
"content": "<tts_text_eod>",
|
| 247 |
+
"lstrip": false,
|
| 248 |
+
"normalized": false,
|
| 249 |
+
"rstrip": false,
|
| 250 |
+
"single_word": false,
|
| 251 |
+
"special": true
|
| 252 |
+
},
|
| 253 |
+
"151674": {
|
| 254 |
+
"content": "<tts_text_bos_single>",
|
| 255 |
+
"lstrip": false,
|
| 256 |
+
"normalized": false,
|
| 257 |
+
"rstrip": false,
|
| 258 |
+
"single_word": false,
|
| 259 |
+
"special": true
|
| 260 |
+
},
|
| 261 |
+
"151675": {
|
| 262 |
+
"content": "<non_speech>",
|
| 263 |
+
"lstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"rstrip": false,
|
| 266 |
+
"single_word": false,
|
| 267 |
+
"special": false
|
| 268 |
+
},
|
| 269 |
+
"151676": {
|
| 270 |
+
"content": "<|audio_pad|>",
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"normalized": false,
|
| 273 |
+
"rstrip": false,
|
| 274 |
+
"single_word": false,
|
| 275 |
+
"special": true
|
| 276 |
+
},
|
| 277 |
+
"151677": {
|
| 278 |
+
"content": "<blank1>",
|
| 279 |
+
"lstrip": false,
|
| 280 |
+
"normalized": false,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"single_word": false,
|
| 283 |
+
"special": true
|
| 284 |
+
},
|
| 285 |
+
"151678": {
|
| 286 |
+
"content": "<blank2>",
|
| 287 |
+
"lstrip": false,
|
| 288 |
+
"normalized": false,
|
| 289 |
+
"rstrip": false,
|
| 290 |
+
"single_word": false,
|
| 291 |
+
"special": true
|
| 292 |
+
},
|
| 293 |
+
"151679": {
|
| 294 |
+
"content": "<blank3>",
|
| 295 |
+
"lstrip": false,
|
| 296 |
+
"normalized": false,
|
| 297 |
+
"rstrip": false,
|
| 298 |
+
"single_word": false,
|
| 299 |
+
"special": true
|
| 300 |
+
},
|
| 301 |
+
"151680": {
|
| 302 |
+
"content": "<blank4>",
|
| 303 |
+
"lstrip": false,
|
| 304 |
+
"normalized": false,
|
| 305 |
+
"rstrip": false,
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"special": true
|
| 308 |
+
},
|
| 309 |
+
"151681": {
|
| 310 |
+
"content": "<blank5>",
|
| 311 |
+
"lstrip": false,
|
| 312 |
+
"normalized": false,
|
| 313 |
+
"rstrip": false,
|
| 314 |
+
"single_word": false,
|
| 315 |
+
"special": true
|
| 316 |
+
},
|
| 317 |
+
"151682": {
|
| 318 |
+
"content": "<blank6>",
|
| 319 |
+
"lstrip": false,
|
| 320 |
+
"normalized": false,
|
| 321 |
+
"rstrip": false,
|
| 322 |
+
"single_word": false,
|
| 323 |
+
"special": true
|
| 324 |
+
},
|
| 325 |
+
"151683": {
|
| 326 |
+
"content": "<blank7>",
|
| 327 |
+
"lstrip": false,
|
| 328 |
+
"normalized": false,
|
| 329 |
+
"rstrip": false,
|
| 330 |
+
"single_word": false,
|
| 331 |
+
"special": true
|
| 332 |
+
},
|
| 333 |
+
"151684": {
|
| 334 |
+
"content": "<blank8>",
|
| 335 |
+
"lstrip": false,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"rstrip": false,
|
| 338 |
+
"single_word": false,
|
| 339 |
+
"special": true
|
| 340 |
+
},
|
| 341 |
+
"151685": {
|
| 342 |
+
"content": "<blank9>",
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"normalized": false,
|
| 345 |
+
"rstrip": false,
|
| 346 |
+
"single_word": false,
|
| 347 |
+
"special": true
|
| 348 |
+
},
|
| 349 |
+
"151686": {
|
| 350 |
+
"content": "<blank10>",
|
| 351 |
+
"lstrip": false,
|
| 352 |
+
"normalized": false,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"single_word": false,
|
| 355 |
+
"special": true
|
| 356 |
+
},
|
| 357 |
+
"151687": {
|
| 358 |
+
"content": "<blank11>",
|
| 359 |
+
"lstrip": false,
|
| 360 |
+
"normalized": false,
|
| 361 |
+
"rstrip": false,
|
| 362 |
+
"single_word": false,
|
| 363 |
+
"special": true
|
| 364 |
+
},
|
| 365 |
+
"151688": {
|
| 366 |
+
"content": "<blank12>",
|
| 367 |
+
"lstrip": false,
|
| 368 |
+
"normalized": false,
|
| 369 |
+
"rstrip": false,
|
| 370 |
+
"single_word": false,
|
| 371 |
+
"special": true
|
| 372 |
+
},
|
| 373 |
+
"151689": {
|
| 374 |
+
"content": "<blank13>",
|
| 375 |
+
"lstrip": false,
|
| 376 |
+
"normalized": false,
|
| 377 |
+
"rstrip": false,
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"special": true
|
| 380 |
+
},
|
| 381 |
+
"151690": {
|
| 382 |
+
"content": "<blank14>",
|
| 383 |
+
"lstrip": false,
|
| 384 |
+
"normalized": false,
|
| 385 |
+
"rstrip": false,
|
| 386 |
+
"single_word": false,
|
| 387 |
+
"special": true
|
| 388 |
+
},
|
| 389 |
+
"151691": {
|
| 390 |
+
"content": "<blank15>",
|
| 391 |
+
"lstrip": false,
|
| 392 |
+
"normalized": false,
|
| 393 |
+
"rstrip": false,
|
| 394 |
+
"single_word": false,
|
| 395 |
+
"special": true
|
| 396 |
+
},
|
| 397 |
+
"151692": {
|
| 398 |
+
"content": "<blank16>",
|
| 399 |
+
"lstrip": false,
|
| 400 |
+
"normalized": false,
|
| 401 |
+
"rstrip": false,
|
| 402 |
+
"single_word": false,
|
| 403 |
+
"special": true
|
| 404 |
+
},
|
| 405 |
+
"151693": {
|
| 406 |
+
"content": "<blank17>",
|
| 407 |
+
"lstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"rstrip": false,
|
| 410 |
+
"single_word": false,
|
| 411 |
+
"special": true
|
| 412 |
+
},
|
| 413 |
+
"151694": {
|
| 414 |
+
"content": "<blank18>",
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"normalized": false,
|
| 417 |
+
"rstrip": false,
|
| 418 |
+
"single_word": false,
|
| 419 |
+
"special": true
|
| 420 |
+
},
|
| 421 |
+
"151695": {
|
| 422 |
+
"content": "<blank19>",
|
| 423 |
+
"lstrip": false,
|
| 424 |
+
"normalized": false,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"single_word": false,
|
| 427 |
+
"special": true
|
| 428 |
+
},
|
| 429 |
+
"151696": {
|
| 430 |
+
"content": "<blank20>",
|
| 431 |
+
"lstrip": false,
|
| 432 |
+
"normalized": false,
|
| 433 |
+
"rstrip": false,
|
| 434 |
+
"single_word": false,
|
| 435 |
+
"special": true
|
| 436 |
+
},
|
| 437 |
+
"151697": {
|
| 438 |
+
"content": "<blank21>",
|
| 439 |
+
"lstrip": false,
|
| 440 |
+
"normalized": false,
|
| 441 |
+
"rstrip": false,
|
| 442 |
+
"single_word": false,
|
| 443 |
+
"special": true
|
| 444 |
+
},
|
| 445 |
+
"151698": {
|
| 446 |
+
"content": "<blank22>",
|
| 447 |
+
"lstrip": false,
|
| 448 |
+
"normalized": false,
|
| 449 |
+
"rstrip": false,
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"special": true
|
| 452 |
+
},
|
| 453 |
+
"151699": {
|
| 454 |
+
"content": "<blank23>",
|
| 455 |
+
"lstrip": false,
|
| 456 |
+
"normalized": false,
|
| 457 |
+
"rstrip": false,
|
| 458 |
+
"single_word": false,
|
| 459 |
+
"special": true
|
| 460 |
+
},
|
| 461 |
+
"151700": {
|
| 462 |
+
"content": "<blank24>",
|
| 463 |
+
"lstrip": false,
|
| 464 |
+
"normalized": false,
|
| 465 |
+
"rstrip": false,
|
| 466 |
+
"single_word": false,
|
| 467 |
+
"special": true
|
| 468 |
+
},
|
| 469 |
+
"151701": {
|
| 470 |
+
"content": "<blank25>",
|
| 471 |
+
"lstrip": false,
|
| 472 |
+
"normalized": false,
|
| 473 |
+
"rstrip": false,
|
| 474 |
+
"single_word": false,
|
| 475 |
+
"special": true
|
| 476 |
+
},
|
| 477 |
+
"151702": {
|
| 478 |
+
"content": "<blank26>",
|
| 479 |
+
"lstrip": false,
|
| 480 |
+
"normalized": false,
|
| 481 |
+
"rstrip": false,
|
| 482 |
+
"single_word": false,
|
| 483 |
+
"special": true
|
| 484 |
+
},
|
| 485 |
+
"151703": {
|
| 486 |
+
"content": "<blank27>",
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"normalized": false,
|
| 489 |
+
"rstrip": false,
|
| 490 |
+
"single_word": false,
|
| 491 |
+
"special": true
|
| 492 |
+
},
|
| 493 |
+
"151704": {
|
| 494 |
+
"content": "<asr_text>",
|
| 495 |
+
"lstrip": false,
|
| 496 |
+
"normalized": false,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"single_word": false,
|
| 499 |
+
"special": false
|
| 500 |
+
}
|
| 501 |
+
},
|
| 502 |
+
"additional_special_tokens": [
|
| 503 |
+
"<|im_start|>",
|
| 504 |
+
"<|im_end|>",
|
| 505 |
+
"<|object_ref_start|>",
|
| 506 |
+
"<|object_ref_end|>",
|
| 507 |
+
"<|box_start|>",
|
| 508 |
+
"<|box_end|>",
|
| 509 |
+
"<|quad_start|>",
|
| 510 |
+
"<|quad_end|>",
|
| 511 |
+
"<|vision_start|>",
|
| 512 |
+
"<|vision_end|>",
|
| 513 |
+
"<|vision_pad|>",
|
| 514 |
+
"<|image_pad|>",
|
| 515 |
+
"<|video_pad|>",
|
| 516 |
+
"<|audio_start|>",
|
| 517 |
+
"<|audio_end|>",
|
| 518 |
+
"<tts_pad>",
|
| 519 |
+
"<tts_text_bos>",
|
| 520 |
+
"<tts_text_bos_single>",
|
| 521 |
+
"<|audio_pad|>"
|
| 522 |
+
],
|
| 523 |
+
"audio_bos_token": "<|audio_start|>",
|
| 524 |
+
"audio_eos_token": "<|audio_end|>",
|
| 525 |
+
"audio_token": "<|audio_pad|>",
|
| 526 |
+
"bos_token": null,
|
| 527 |
+
"clean_up_tokenization_spaces": false,
|
| 528 |
+
"eos_token": "<|im_end|>",
|
| 529 |
+
"errors": "replace",
|
| 530 |
+
"extra_special_tokens": {
|
| 531 |
+
"audio_bos_token": "<|audio_start|>",
|
| 532 |
+
"audio_eos_token": "<|audio_end|>",
|
| 533 |
+
"audio_token": "<|audio_pad|>",
|
| 534 |
+
"image_token": "<|image_pad|>",
|
| 535 |
+
"video_token": "<|video_pad|>",
|
| 536 |
+
"vision_bos_token": "<|vision_start|>",
|
| 537 |
+
"vision_eos_token": "<|vision_end|>"
|
| 538 |
+
},
|
| 539 |
+
"fix_mistral_regex": true,
|
| 540 |
+
"image_token": "<|image_pad|>",
|
| 541 |
+
"model_max_length": 131072,
|
| 542 |
+
"pad_token": "<|endoftext|>",
|
| 543 |
+
"processor_class": "Qwen3ASRProcessor",
|
| 544 |
+
"split_special_tokens": false,
|
| 545 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 546 |
+
"unk_token": null,
|
| 547 |
+
"video_token": "<|video_pad|>",
|
| 548 |
+
"vision_bos_token": "<|vision_start|>",
|
| 549 |
+
"vision_eos_token": "<|vision_end|>"
|
| 550 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:138a4ca85f2f4c106299a39b9efe0d880061781663d28ff208e7034d60640e3c
|
| 3 |
+
size 5969
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|