OpenBMB/MiniCPM-o-2_6
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: OpenBMB/MiniCPM-o-2_6
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-10-07 21:30:15 +08:00
commit d565411ba2
41 changed files with 163098 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
assets/Skiing.mp4 Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:479ace116d6ac92487ad90f415b3ef817cd019bba4521043ef0d5faaa1a8415d
size 8534409

3
assets/Vocos.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:09a670eda1c08b740013679c7a90ebb7f1a97646ea7673069a6838e6b51d6c58
size 54363119

389
assets/chattts_tokenizer/special_tokens_map.json Normal file
View File

@@ -0,0 +1,389 @@
{
"additional_special_tokens": [
{
"content": "[Sasr]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[Pasr]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[Easr]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[Stts]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[Ptts]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[Etts]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[Sbreak]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[Pbreak]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[Ebreak]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[uv_break]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[v_break]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[lbreak]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[llbreak]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[undefine]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[laugh]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[spk_emb]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[empty_spk]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[music]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[pure]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[break_0]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[break_1]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[break_2]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[break_3]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[break_4]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[break_5]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[break_6]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[break_7]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[laugh_0]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[laugh_1]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[laugh_2]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[oral_0]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[oral_1]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[oral_2]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[oral_3]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[oral_4]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[oral_5]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[oral_6]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[oral_7]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[oral_8]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[oral_9]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[speed_0]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[speed_1]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[speed_2]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[speed_3]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[speed_4]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[speed_5]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[speed_6]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[speed_7]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[speed_8]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
{
"content": "[speed_9]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
],
"cls_token": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"mask_token": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"sep_token": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

BIN
assets/chattts_tokenizer/tokenizer.json (Stored with Git LFS) Normal file
View File

Binary file not shown.

516
assets/chattts_tokenizer/tokenizer_config.json Normal file
View File

@@ -0,0 +1,516 @@
{
"added_tokens_decoder": {
"0": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"101": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"102": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"103": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21128": {
"content": "[Sasr]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21129": {
"content": "[Pasr]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21130": {
"content": "[Easr]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21131": {
"content": "[Stts]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21132": {
"content": "[Ptts]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21133": {
"content": "[Etts]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21134": {
"content": "[Sbreak]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21135": {
"content": "[Pbreak]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21136": {
"content": "[Ebreak]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21137": {
"content": "[uv_break]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21138": {
"content": "[v_break]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21139": {
"content": "[lbreak]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21140": {
"content": "[llbreak]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21141": {
"content": "[undefine]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21142": {
"content": "[laugh]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21143": {
"content": "[spk_emb]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21144": {
"content": "[empty_spk]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21145": {
"content": "[music]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21146": {
"content": "[pure]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21147": {
"content": "[break_0]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21148": {
"content": "[break_1]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21149": {
"content": "[break_2]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21150": {
"content": "[break_3]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21151": {
"content": "[break_4]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21152": {
"content": "[break_5]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21153": {
"content": "[break_6]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21154": {
"content": "[break_7]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21155": {
"content": "[laugh_0]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21156": {
"content": "[laugh_1]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21157": {
"content": "[laugh_2]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21158": {
"content": "[oral_0]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21159": {
"content": "[oral_1]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21160": {
"content": "[oral_2]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21161": {
"content": "[oral_3]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21162": {
"content": "[oral_4]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21163": {
"content": "[oral_5]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21164": {
"content": "[oral_6]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21165": {
"content": "[oral_7]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21166": {
"content": "[oral_8]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21167": {
"content": "[oral_9]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21168": {
"content": "[speed_0]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21169": {
"content": "[speed_1]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21170": {
"content": "[speed_2]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21171": {
"content": "[speed_3]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21172": {
"content": "[speed_4]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21173": {
"content": "[speed_5]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21174": {
"content": "[speed_6]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21175": {
"content": "[speed_7]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21176": {
"content": "[speed_8]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"21177": {
"content": "[speed_9]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"[Sasr]",
"[Pasr]",
"[Easr]",
"[Stts]",
"[Ptts]",
"[Etts]",
"[Sbreak]",
"[Pbreak]",
"[Ebreak]",
"[uv_break]",
"[v_break]",
"[lbreak]",
"[llbreak]",
"[undefine]",
"[laugh]",
"[spk_emb]",
"[empty_spk]",
"[music]",
"[pure]",
"[break_0]",
"[break_1]",
"[break_2]",
"[break_3]",
"[break_4]",
"[break_5]",
"[break_6]",
"[break_7]",
"[laugh_0]",
"[laugh_1]",
"[laugh_2]",
"[oral_0]",
"[oral_1]",
"[oral_2]",
"[oral_3]",
"[oral_4]",
"[oral_5]",
"[oral_6]",
"[oral_7]",
"[oral_8]",
"[oral_9]",
"[speed_0]",
"[speed_1]",
"[speed_2]",
"[speed_3]",
"[speed_4]",
"[speed_5]",
"[speed_6]",
"[speed_7]",
"[speed_8]",
"[speed_9]"
],
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"do_basic_tokenize": true,
"do_lower_case": true,
"mask_token": "[MASK]",
"max_length": 256,
"model_max_length": 1000000000000000019884624838656,
"never_split": null,
"pad_to_multiple_of": null,
"pad_token": "[PAD]",
"pad_token_type_id": 0,
"padding_side": "right",
"sep_token": "[SEP]",
"stride": 0,
"strip_accents": null,
"tokenize_chinese_chars": true,
"tokenizer_class": "BertTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "[UNK]"
}

3
assets/demo.wav Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:d0b347d8ed0b2314c0d175fbdac79f6f3f91a6402bd7492ac5c860646a2ba309
size 1454196

BIN
assets/input_examples/Trump_WEF_2018_10s.mp3 Normal file
View File

Binary file not shown.

3
assets/input_examples/assistant_default_female_voice.wav Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2ee6f84892e693bd2bb478608db0c9a2459b936af3283697b006cfd969c75484
size 224044

3
assets/input_examples/assistant_female_voice.wav Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1d712ba6de1d15d52eda96bdc043ce43eb5af4b4ac441b78b6fb0fdaf6683c7a
size 235244

3
assets/input_examples/assistant_male_voice.wav Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e6b5eff26be104bbfc039f31f8cebcd6f329c275ccafa01234856ec1a964e999
size 144044

BIN
assets/input_examples/audio_understanding.mp3 Normal file
View File

Binary file not shown.

3
assets/input_examples/chi-english-1.wav Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9e859f2fcd4664da461209577ac1b62fa2a2c4185ddddc4a63726530a18744e1
size 492198

3
assets/input_examples/cxk_original.wav Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dbb0860cb4dd7c7003b6f0406299fc7c0febc5c6a990e1c670d29b763e84e7ed
size 384046

3
assets/input_examples/exciting-emotion.wav Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5dd68efbb93cb388dc598404cf8af106bf063ddc9f8ae4460f11189f0b3ed4ed
size 696044

3
assets/input_examples/fast-pace.wav Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dfad5114ceee7b64b37866f3ed3418fe2eb99b178574a7319ad076dc26b746ec
size 986444

3
assets/input_examples/icl_20.wav Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:53892ece071342958403bc5643f84169a30b89cc0fc79eb69508bfa11dd85e68
size 618528

3
assets/input_examples/indian-accent.wav Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:716533af9ec8ca4586035af7dce4a65ce93e851d3f2474242d401b50bf3c0cdc
size 1408844