Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- checkpoints/v5/chat_template.jinja +89 -0
- checkpoints/v5/config.json +105 -0
- checkpoints/v5/model.safetensors +3 -0
- checkpoints/v5/optimizer.bin +3 -0
- checkpoints/v5/random_states_0.pkl +3 -0
- checkpoints/v5/scheduler.bin +3 -0
- checkpoints/v5/tokenizer.json +3 -0
- checkpoints/v5/tokenizer_config.json +23 -0
- checkpoints/v5/train_config.json +110 -0
.gitattributes
CHANGED
|
@@ -36,3 +36,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 36 |
checkpoints/v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
checkpoints/v2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
checkpoints/v3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 36 |
checkpoints/v1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 37 |
checkpoints/v2/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 38 |
checkpoints/v3/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
checkpoints/v5/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
checkpoints/v5/chat_template.jinja
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant\n' }}
|
| 86 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- endif %}
|
checkpoints/v5/config.json
ADDED
|
@@ -0,0 +1,105 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"OmniVoice"
|
| 4 |
+
],
|
| 5 |
+
"attn_implementation": "flex_attention",
|
| 6 |
+
"audio_codebook_weights": [
|
| 7 |
+
8,
|
| 8 |
+
8,
|
| 9 |
+
6,
|
| 10 |
+
6,
|
| 11 |
+
4,
|
| 12 |
+
4,
|
| 13 |
+
2,
|
| 14 |
+
2
|
| 15 |
+
],
|
| 16 |
+
"audio_mask_id": 1024,
|
| 17 |
+
"audio_vocab_size": 1025,
|
| 18 |
+
"bos_token_id": null,
|
| 19 |
+
"compile_flex_attention_mask": false,
|
| 20 |
+
"dtype": "float32",
|
| 21 |
+
"eos_token_id": 151645,
|
| 22 |
+
"llm_config": {
|
| 23 |
+
"_name_or_path": "",
|
| 24 |
+
"architectures": [
|
| 25 |
+
"Qwen3ForCausalLM"
|
| 26 |
+
],
|
| 27 |
+
"attention_bias": false,
|
| 28 |
+
"attention_dropout": 0.0,
|
| 29 |
+
"bos_token_id": 151643,
|
| 30 |
+
"chunk_size_feed_forward": 0,
|
| 31 |
+
"dtype": "float32",
|
| 32 |
+
"eos_token_id": 151645,
|
| 33 |
+
"head_dim": 128,
|
| 34 |
+
"hidden_act": "silu",
|
| 35 |
+
"hidden_size": 1024,
|
| 36 |
+
"id2label": {
|
| 37 |
+
"0": "LABEL_0",
|
| 38 |
+
"1": "LABEL_1"
|
| 39 |
+
},
|
| 40 |
+
"initializer_range": 0.02,
|
| 41 |
+
"intermediate_size": 3072,
|
| 42 |
+
"is_encoder_decoder": false,
|
| 43 |
+
"label2id": {
|
| 44 |
+
"LABEL_0": 0,
|
| 45 |
+
"LABEL_1": 1
|
| 46 |
+
},
|
| 47 |
+
"layer_types": [
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention",
|
| 51 |
+
"full_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"full_attention",
|
| 55 |
+
"full_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"full_attention",
|
| 59 |
+
"full_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"full_attention",
|
| 63 |
+
"full_attention",
|
| 64 |
+
"full_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"full_attention",
|
| 67 |
+
"full_attention",
|
| 68 |
+
"full_attention",
|
| 69 |
+
"full_attention",
|
| 70 |
+
"full_attention",
|
| 71 |
+
"full_attention",
|
| 72 |
+
"full_attention",
|
| 73 |
+
"full_attention",
|
| 74 |
+
"full_attention",
|
| 75 |
+
"full_attention"
|
| 76 |
+
],
|
| 77 |
+
"max_position_embeddings": 40960,
|
| 78 |
+
"max_window_layers": 28,
|
| 79 |
+
"model_type": "qwen3",
|
| 80 |
+
"num_attention_heads": 16,
|
| 81 |
+
"num_hidden_layers": 28,
|
| 82 |
+
"num_key_value_heads": 8,
|
| 83 |
+
"output_attentions": false,
|
| 84 |
+
"output_hidden_states": false,
|
| 85 |
+
"pad_token_id": null,
|
| 86 |
+
"problem_type": null,
|
| 87 |
+
"return_dict": true,
|
| 88 |
+
"rms_norm_eps": 1e-06,
|
| 89 |
+
"rope_parameters": {
|
| 90 |
+
"rope_theta": 1000000,
|
| 91 |
+
"rope_type": "default"
|
| 92 |
+
},
|
| 93 |
+
"sliding_window": null,
|
| 94 |
+
"tie_word_embeddings": true,
|
| 95 |
+
"use_cache": true,
|
| 96 |
+
"use_sliding_window": false,
|
| 97 |
+
"vocab_size": 151676
|
| 98 |
+
},
|
| 99 |
+
"loss_label_smoothing": 0.02,
|
| 100 |
+
"model_type": "omnivoice",
|
| 101 |
+
"num_audio_codebook": 8,
|
| 102 |
+
"pad_token_id": 151643,
|
| 103 |
+
"transformers_version": "5.5.4",
|
| 104 |
+
"validate_audio_token_range": true
|
| 105 |
+
}
|
checkpoints/v5/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8fdff0b653ced91e1909a1c28a9cfb79ee393f3da2e511bb02661b9ab70b1a8
|
| 3 |
+
size 3256018588
|
checkpoints/v5/optimizer.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7748d4c2456027d60fb4501e30b30274e9469f136e718e4625349c2c15695019
|
| 3 |
+
size 4900882075
|
checkpoints/v5/random_states_0.pkl
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c7e46ff2a82e2dd68c3c47b0709c21c8517ecbe48d5873c1d25b49d59560e295
|
| 3 |
+
size 14821
|
checkpoints/v5/scheduler.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4795bc17bb004c1b0ac8584f97235ecbc992891000c00b8258131394ede6f5ed
|
| 3 |
+
size 1465
|
checkpoints/v5/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:408f669b7e2b045fdf54201d815bd364e6667dbd845115da81239c40bc6dcfd1
|
| 3 |
+
size 11423986
|
checkpoints/v5/tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|im_end|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|denoise|>",
|
| 10 |
+
"<|lang_start|>",
|
| 11 |
+
"<|lang_end|>",
|
| 12 |
+
"<|instruct_start|>",
|
| 13 |
+
"<|instruct_end|>",
|
| 14 |
+
"<|text_start|>",
|
| 15 |
+
"<|text_end|>"
|
| 16 |
+
],
|
| 17 |
+
"is_local": false,
|
| 18 |
+
"model_max_length": 131072,
|
| 19 |
+
"pad_token": "<|endoftext|>",
|
| 20 |
+
"split_special_tokens": false,
|
| 21 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 22 |
+
"unk_token": null
|
| 23 |
+
}
|
checkpoints/v5/train_config.json
ADDED
|
@@ -0,0 +1,110 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"output_dir": "/home/infidea/suwon/omni-voice-advance-plus/exp/omnivoice_0.6B-FT-loss_ablation",
|
| 3 |
+
"data_config": "/home/infidea/suwon/omni-voice-advance-plus/examples/config/data_config_finetune_advance_plus.json",
|
| 4 |
+
"llm_name_or_path": "Qwen/Qwen3-0.6B",
|
| 5 |
+
"tokenizer_name_or_path": "Qwen/Qwen3-0.6B",
|
| 6 |
+
"expected_llm_model_type": "qwen3",
|
| 7 |
+
"expected_llm_hidden_size": 1024,
|
| 8 |
+
"expected_llm_intermediate_size": 3072,
|
| 9 |
+
"expected_llm_num_hidden_layers": 28,
|
| 10 |
+
"expected_llm_num_attention_heads": 16,
|
| 11 |
+
"expected_llm_num_key_value_heads": 8,
|
| 12 |
+
"expected_llm_vocab_size": 151936,
|
| 13 |
+
"audio_vocab_size": 1025,
|
| 14 |
+
"audio_mask_id": 1024,
|
| 15 |
+
"num_audio_codebook": 8,
|
| 16 |
+
"audio_codebook_weights": [
|
| 17 |
+
8,
|
| 18 |
+
8,
|
| 19 |
+
6,
|
| 20 |
+
6,
|
| 21 |
+
4,
|
| 22 |
+
4,
|
| 23 |
+
2,
|
| 24 |
+
2
|
| 25 |
+
],
|
| 26 |
+
"drop_cond_ratio": 0.1,
|
| 27 |
+
"prompt_ratio_range": [
|
| 28 |
+
0.0,
|
| 29 |
+
0.3
|
| 30 |
+
],
|
| 31 |
+
"mask_ratio_range": [
|
| 32 |
+
0.3,
|
| 33 |
+
1.0
|
| 34 |
+
],
|
| 35 |
+
"min_masked_audio_tokens": 8,
|
| 36 |
+
"language_ratio": 0.8,
|
| 37 |
+
"use_pinyin_ratio": 0.0,
|
| 38 |
+
"instruct_ratio": 1.0,
|
| 39 |
+
"only_instruct_ratio": 0.5,
|
| 40 |
+
"log_codebook_losses": true,
|
| 41 |
+
"loss_label_smoothing": 0.02,
|
| 42 |
+
"resume_from_checkpoint": null,
|
| 43 |
+
"init_from_checkpoint": "k2-fsa/OmniVoice",
|
| 44 |
+
"learning_rate": 5e-05,
|
| 45 |
+
"weight_decay": 0.01,
|
| 46 |
+
"max_grad_norm": 1.0,
|
| 47 |
+
"steps": 1000000,
|
| 48 |
+
"seed": 42,
|
| 49 |
+
"lr_scheduler_type": "cosine",
|
| 50 |
+
"warmup_type": "ratio",
|
| 51 |
+
"warmup_ratio": 0.01,
|
| 52 |
+
"warmup_steps": 0,
|
| 53 |
+
"batch_tokens": 8192,
|
| 54 |
+
"gradient_accumulation_steps": 4,
|
| 55 |
+
"num_workers": 1,
|
| 56 |
+
"mixed_precision": "bf16",
|
| 57 |
+
"allow_tf32": true,
|
| 58 |
+
"require_cuda": true,
|
| 59 |
+
"use_deepspeed": false,
|
| 60 |
+
"deepspeed_config": null,
|
| 61 |
+
"compile_flex_attention_mask": false,
|
| 62 |
+
"validate_audio_token_range": true,
|
| 63 |
+
"skip_bad_batches": true,
|
| 64 |
+
"max_consecutive_batch_skips": 50,
|
| 65 |
+
"attn_implementation": "flex_attention",
|
| 66 |
+
"logging_steps": 50,
|
| 67 |
+
"eval_steps": 500,
|
| 68 |
+
"save_steps": 500,
|
| 69 |
+
"keep_last_n_checkpoints": 3,
|
| 70 |
+
"use_wandb": true,
|
| 71 |
+
"wandb_project": "omnivoice_advance_plus_upgrade",
|
| 72 |
+
"wandb_entity": null,
|
| 73 |
+
"wandb_run_name": null,
|
| 74 |
+
"wandb_group": null,
|
| 75 |
+
"wandb_tags": [],
|
| 76 |
+
"wandb_mode": null,
|
| 77 |
+
"inference_logging_steps": 500,
|
| 78 |
+
"inference_logging_text": null,
|
| 79 |
+
"inference_logging_language": null,
|
| 80 |
+
"inference_logging_ref_audio": null,
|
| 81 |
+
"inference_logging_ref_text": null,
|
| 82 |
+
"inference_logging_num_step": 32,
|
| 83 |
+
"inference_logging_guidance_scale": 2.0,
|
| 84 |
+
"inference_logging_speed": 1.0,
|
| 85 |
+
"inference_logging_duration": null,
|
| 86 |
+
"inference_audio_tokenizer_path": null,
|
| 87 |
+
"inference_logging_jsonl_dir": [
|
| 88 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/zs_data_all/ch_data/txts",
|
| 89 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/zs_data_all/en_data/txts",
|
| 90 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/zs_data_all/fr_data/txts",
|
| 91 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/zs_data_all/ja_data/txts",
|
| 92 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/zs_data_all/ko_data/txts",
|
| 93 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/zs_data_all/pre_ch_data/txts",
|
| 94 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/zs_data_all/sp_data/txts",
|
| 95 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/zs_data_all/vi_data/txts"
|
| 96 |
+
],
|
| 97 |
+
"inference_logging_voice_design_jsonl_dir": [
|
| 98 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/voice_design_all/ch/txts",
|
| 99 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/voice_design_all/en/txts",
|
| 100 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/voice_design_all/de/txts",
|
| 101 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/voice_design_all/es/txts",
|
| 102 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/voice_design_all/fr/txts",
|
| 103 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/voice_design_all/ja/txts",
|
| 104 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/voice_design_all/ko/txts",
|
| 105 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/voice_design_all/ru/txts",
|
| 106 |
+
"/home/infidea/tts-data/suwon/OmniVoice_data/voice_design_all/vi/txts"
|
| 107 |
+
],
|
| 108 |
+
"inference_logging_save_eval_artifacts": true,
|
| 109 |
+
"inference_logging_eval_dir": null
|
| 110 |
+
}
|