Files
1038lab-ComfyUI-QwenASR/example_workflows/ComfyUI-QwenASR.json
T
2026-09-11 17:41:23 -07:00

398 lines
8.8 KiB
JSON

{
"id": "9d04e057-545b-4e74-a920-6d54c2095ab7",
"revision": 0,
"last_node_id": 44,
"last_link_id": 65,
"nodes": [
{
"id": 33,
"type": "MarkdownNote",
"pos": [
2466.4190965484545,
5540.207540564256
],
"size": [
282.78125,
227.234375
],
"flags": {},
"order": 0,
"mode": 0,
"inputs": [],
"outputs": [],
"properties": {
"ue_properties": {
"widget_ue_connectable": {},
"version": "7.5.2",
"input_ue_unconnectable": {}
}
},
"widgets_values": [
"### ASR Hints (Optional)\n\n Use **Hints** to force correct brand names / casing.\n\n Example:\n\n Important terms: ComfyUI, Qwen3-ASR, HuggingFace, ModelScope\n Prefer brand spellings exactly as written above.\n\n\n - If you leave Hints empty, ASR uses default behavior.\n - Hints are best for proper nouns, brands, and special terms."
],
"widgets_values_named": {
"text": "### ASR Hints (Optional)\n\n Use **Hints** to force correct brand names / casing.\n\n Example:\n\n Important terms: ComfyUI, Qwen3-ASR, HuggingFace, ModelScope\n Prefer brand spellings exactly as written above.\n\n\n - If you leave Hints empty, ASR uses default behavior.\n - Hints are best for proper nouns, brands, and special terms."
},
"color": "#432",
"bgcolor": "#653"
},
{
"id": 39,
"type": "AILab_Qwen3ASR",
"pos": [
2787.180380681309,
5336.359243143102
],
"size": [
340,
242
],
"flags": {},
"order": 2,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "AUDIO",
"link": 58
}
],
"outputs": [
{
"name": "TEXT",
"type": "STRING",
"links": [
59
]
}
],
"properties": {
"cnr_id": "ComfyUI-QwenASR",
"ver": "b4a72ce9edff506f1659c059891da8d98b73284b",
"Node name for S&R": "AILab_Qwen3ASR",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.8"
}
},
"widgets_values": [
"Qwen/Qwen3-ASR-0.6B-hf",
"bf16",
"auto",
"",
true,
true
],
"widgets_values_named": {
"model": "Qwen/Qwen3-ASR-0.6B-hf",
"precision": "bf16",
"language": "auto",
"hints": "",
"normalize_text": true,
"unload_models": true
},
"color": "#151c19",
"bgcolor": "#444d49"
},
{
"id": 24,
"type": "PreviewAny",
"pos": [
3151.720433669072,
5341.723573209056
],
"size": [
681.46875,
255.828125
],
"flags": {},
"order": 4,
"mode": 0,
"inputs": [
{
"name": "source",
"type": "*",
"link": 59
}
],
"outputs": [
{
"name": "STRING",
"type": "STRING",
"links": null
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.11.0",
"Node name for S&R": "PreviewAny",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.5.2"
}
},
"widgets_values": [],
"widgets_values_named": {}
},
{
"id": 5,
"type": "LoadAudio",
"pos": [
2466.4190965484545,
5336.359243143102
],
"size": [
282.78125,
138
],
"flags": {},
"order": 1,
"mode": 0,
"inputs": [],
"outputs": [
{
"name": "AUDIO",
"type": "AUDIO",
"links": [
58,
64
]
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.11.0",
"Node name for S&R": "LoadAudio",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.5.2"
}
},
"widgets_values": [
"comfyui-qwenasr_V1.1.0.mp4",
null,
null
],
"widgets_values_named": {
"audio": "comfyui-qwenasr_V1.1.0.mp4",
"upload": null
}
},
{
"id": 35,
"type": "PreviewAny",
"pos": [
3140.7646353022187,
5710.311146853169
],
"size": [
688.546875,
415.203125
],
"flags": {},
"order": 5,
"mode": 0,
"inputs": [
{
"name": "source",
"type": "*",
"link": 65
}
],
"outputs": [
{
"name": "STRING",
"type": "STRING",
"links": null
}
],
"properties": {
"cnr_id": "comfy-core",
"ver": "0.11.0",
"Node name for S&R": "PreviewAny",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.5.2"
}
},
"widgets_values": [],
"widgets_values_named": {}
},
{
"id": 44,
"type": "AILab_Qwen3ASRSubtitle",
"pos": [
2784.7420178280763,
5689.991663110041
],
"size": [
340,
561.984375
],
"flags": {},
"order": 3,
"mode": 0,
"inputs": [
{
"name": "audio",
"type": "AUDIO",
"link": 64
}
],
"outputs": [
{
"name": "TEXT",
"type": "STRING",
"links": null
},
{
"name": "SUBTITLES",
"type": "STRING",
"links": [
65
]
},
{
"name": "LANGUAGE",
"type": "STRING",
"links": null
},
{
"name": "OUTPUT_PATH",
"type": "STRING",
"links": null
}
],
"properties": {
"cnr_id": "ComfyUI-QwenASR",
"ver": "b4a72ce9edff506f1659c059891da8d98b73284b",
"Node name for S&R": "AILab_Qwen3ASRSubtitle",
"ue_properties": {
"widget_ue_connectable": {},
"input_ue_unconnectable": {},
"version": "7.8"
}
},
"widgets_values": [
"Qwen/Qwen3-ASR-0.6B-hf",
"bf16",
"auto",
"Qwen/Qwen3-ForcedAligner-0.6B-hf",
"auto",
"",
"none",
"",
"split_by_punctuation_or_pause",
0.6,
40,
32,
256,
true,
true
],
"widgets_values_named": {
"model": "Qwen/Qwen3-ASR-0.6B-hf",
"precision": "bf16",
"attention": "auto",
"forced_aligner": "Qwen/Qwen3-ForcedAligner-0.6B-hf",
"language": "auto",
"hints": "",
"output_format": "none",
"output_path": "",
"split_mode": "split_by_punctuation_or_pause",
"max_gap_sec": 0.6,
"max_chars": 40,
"max_inference_batch_size": 32,
"max_new_tokens": 256,
"normalize_text": true,
"unload_models": true
},
"color": "#151c19",
"bgcolor": "#444d49"
}
],
"links": [
[
58,
5,
0,
39,
0,
"AUDIO"
],
[
59,
39,
0,
24,
0,
"STRING"
],
[
64,
5,
0,
44,
0,
"AUDIO"
],
[
65,
44,
1,
35,
0,
"STRING"
]
],
"groups": [
{
"id": 1,
"title": "QwenASR without hints",
"bounding": [
2777.180380681309,
5262.759243143101,
1064.8994521188579,
341.40172024181356
],
"color": "#3f789e",
"flags": {}
},
{
"id": 2,
"title": "QwenASR Subtitle",
"bounding": [
2775.6361296817013,
5615.73824954861,
1063.7871702224647,
642.6388561949889
],
"color": "#3f789e",
"flags": {}
}
],
"config": {},
"extra": {
"workflowRendererVersion": "LG",
"ue_links": [],
"ds": {
"scale": 0.9842769753815471,
"offset": [
-2167.1743053632754,
-5092.025295565281
]
},
"links_added_by_ue": [],
"frontendVersion": "1.51.10",
"VHS_latentpreview": false,
"VHS_latentpreviewrate": 0,
"VHS_MetadataImage": true,
"VHS_KeepIntermediate": true
},
"version": 0.4,
"seed_widgets": {}
}