michsethowusu commited on
Commit
e972f71
·
verified ·
1 Parent(s): e24cce8

Upload merged KaniTTS fine‑tuned on Asante Twi

Browse files
README.md ADDED
@@ -0,0 +1,13 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - tw
5
+ pipeline_tag: text-to-speech
6
+ tags:
7
+ - kani-tts
8
+ - fine-tuned
9
+ - asante-twi
10
+ - lora
11
+ ---
12
+
13
+ KaniTTS fine‑tuned on Asante Twi Bible speech data.
chat_template.jinja ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {{- bos_token -}}
2
+ {%- set system_prompt = "" -%}
3
+ {%- set ns = namespace(system_prompt="") -%}
4
+ {%- if messages[0]["role"] == "system" -%}
5
+ {%- set ns.system_prompt = messages[0]["content"] -%}
6
+ {%- set messages = messages[1:] -%}
7
+ {%- endif -%}
8
+ {%- if tools -%}
9
+ {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: <|tool_list_start|>[" -%}
10
+ {%- for tool in tools -%}
11
+ {%- if tool is not string -%}
12
+ {%- set tool = tool | tojson -%}
13
+ {%- endif -%}
14
+ {%- set ns.system_prompt = ns.system_prompt + tool -%}
15
+ {%- if not loop.last -%}
16
+ {%- set ns.system_prompt = ns.system_prompt + ", " -%}
17
+ {%- endif -%}
18
+ {%- endfor -%}
19
+ {%- set ns.system_prompt = ns.system_prompt + "]<|tool_list_end|>" -%}
20
+ {%- endif -%}
21
+ {%- if ns.system_prompt -%}
22
+ {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
23
+ {%- endif -%}
24
+ {%- for message in messages -%}
25
+ {{- "<|im_start|>" + message["role"] + "\n" -}}
26
+ {%- set content = message["content"] -%}
27
+ {%- if content is not string -%}
28
+ {%- set content = content | tojson -%}
29
+ {%- endif -%}
30
+ {%- if message["role"] == "tool" -%}
31
+ {%- set content = "<|tool_response_start|>" + content + "<|tool_response_end|>" -%}
32
+ {%- endif -%}
33
+ {{- content + "<|im_end|>\n" -}}
34
+ {%- endfor -%}
35
+ {%- if add_generation_prompt -%}
36
+ {{- "<|im_start|>assistant\n" -}}
37
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,61 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Lfm2ForCausalLM"
4
+ ],
5
+ "block_auto_adjust_ff_dim": true,
6
+ "block_dim": 1024,
7
+ "block_ffn_dim_multiplier": 1.0,
8
+ "block_mlp_init_scale": 1.0,
9
+ "block_multiple_of": 256,
10
+ "block_norm_eps": 1e-05,
11
+ "block_out_init_scale": 1.0,
12
+ "block_use_swiglu": true,
13
+ "block_use_xavier_init": true,
14
+ "bos_token_id": 1,
15
+ "conv_L_cache": 3,
16
+ "conv_bias": false,
17
+ "conv_dim": 1024,
18
+ "conv_dim_out": 1024,
19
+ "conv_use_xavier_init": true,
20
+ "dtype": "bfloat16",
21
+ "eos_token_id": 7,
22
+ "full_attn_idxs": null,
23
+ "hidden_size": 1024,
24
+ "initializer_range": 0.02,
25
+ "intermediate_size": 6656,
26
+ "layer_types": [
27
+ "conv",
28
+ "conv",
29
+ "full_attention",
30
+ "conv",
31
+ "conv",
32
+ "full_attention",
33
+ "conv",
34
+ "conv",
35
+ "full_attention",
36
+ "conv",
37
+ "full_attention",
38
+ "conv",
39
+ "full_attention",
40
+ "conv",
41
+ "full_attention",
42
+ "conv"
43
+ ],
44
+ "max_position_embeddings": 128000,
45
+ "model_type": "lfm2",
46
+ "norm_eps": 1e-05,
47
+ "num_attention_heads": 16,
48
+ "num_heads": 16,
49
+ "num_hidden_layers": 16,
50
+ "num_key_value_heads": 8,
51
+ "pad_token_id": 0,
52
+ "rope_parameters": {
53
+ "rope_theta": 1000000.0,
54
+ "rope_type": "default"
55
+ },
56
+ "tie_word_embeddings": true,
57
+ "transformers_version": "5.8.1",
58
+ "use_cache": true,
59
+ "use_pos_enc": true,
60
+ "vocab_size": 80539
61
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 7,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "5.0.0.dev0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecaf5af591753260344c81166e4f12487a842605035631eee80a1fdf3c9957d5
3
+ size 739710608
special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|im_end|>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|pad|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "backend": "tokenizers",
3
+ "bos_token": "<|startoftext|>",
4
+ "clean_up_tokenization_spaces": true,
5
+ "eos_token": "<|im_end|>",
6
+ "is_local": false,
7
+ "legacy": false,
8
+ "local_files_only": false,
9
+ "model_input_names": [
10
+ "input_ids",
11
+ "attention_mask"
12
+ ],
13
+ "model_max_length": 1000000000000000019884624838656,
14
+ "pad_token": "<|pad|>",
15
+ "sp_model_kwargs": {},
16
+ "spaces_between_special_tokens": false,
17
+ "tokenizer_class": "TokenizersBackend",
18
+ "use_default_system_prompt": false,
19
+ "use_fast": true
20
+ }