Hugging Face's logo

TheRamsay
/
wav2vec2-gpt2-enc-dec

Automatic Speech Recognition
Transformers
Safetensors
speech-encoder-decoder
Generated from Trainer
Eval Results
Model card Files
xet
Community
TheRamsay commited on
Commit
e506bc0
·
verified ·
1 Parent(s): f3e8512

Training in progress, epoch 1

Browse files
Files changed (7) hide show
  1. config.json +10 -11
  2. merges.txt +0 -0
  3. model.safetensors +2 -2
  4. special_tokens_map.json +3 -3
  5. tokenizer.json +0 -0
  6. tokenizer_config.json +1 -2
  7. vocab.json +0 -0
config.json CHANGED
@@ -3,8 +3,8 @@
3
  "SpeechEncoderDecoderModel"
4
  ],
5
  "decoder": {
6
- "_name_or_path": "fav-kky/gpt2-small-cs",
7
- "activation_function": "gelu",
8
  "add_cross_attention": true,
9
  "architectures": [
10
  "GPT2LMHeadModel"
@@ -12,7 +12,7 @@
12
  "attn_pdrop": 0.1,
13
  "bad_words_ids": null,
14
  "begin_suppress_tokens": null,
15
- "bos_token_id": 0,
16
  "chunk_size_feed_forward": 0,
17
  "cross_attention_hidden_size": null,
18
  "decoder_start_token_id": null,
@@ -21,12 +21,11 @@
21
  "early_stopping": false,
22
  "embd_pdrop": 0.1,
23
  "encoder_no_repeat_ngram_size": 0,
24
- "eos_token_id": 0,
25
  "exponential_decay_length_penalty": null,
26
  "finetuning_task": null,
27
  "forced_bos_token_id": null,
28
  "forced_eos_token_id": null,
29
- "gradient_checkpointing": false,
30
  "id2label": {
31
  "0": "LABEL_0",
32
  "1": "LABEL_1"
@@ -44,10 +43,10 @@
44
  "min_length": 0,
45
  "model_type": "gpt2",
46
  "n_ctx": 1024,
47
- "n_embd": 512,
48
- "n_head": 8,
49
  "n_inner": null,
50
- "n_layer": 4,
51
  "n_positions": 1024,
52
  "no_repeat_ngram_size": 0,
53
  "num_beam_groups": 1,
@@ -78,7 +77,7 @@
78
  "task_specific_params": {
79
  "text-generation": {
80
  "do_sample": true,
81
- "max_length": 1024
82
  }
83
  },
84
  "temperature": 1.0,
@@ -93,7 +92,7 @@
93
  "typical_p": 1.0,
94
  "use_bfloat16": false,
95
  "use_cache": true,
96
- "vocab_size": 50000
97
  },
98
  "decoder_start_token_id": 0,
99
  "encoder": {
@@ -256,7 +255,7 @@
256
  "vocab_size": 32,
257
  "xvector_output_dim": 512
258
  },
259
- "eos_token_id": 0,
260
  "is_encoder_decoder": true,
261
  "model_type": "speech-encoder-decoder",
262
  "pad_token_id": 0,
 
3
  "SpeechEncoderDecoderModel"
4
  ],
5
  "decoder": {
6
+ "_name_or_path": "spital/gpt2-small-czech-cs",
7
+ "activation_function": "gelu_new",
8
  "add_cross_attention": true,
9
  "architectures": [
10
  "GPT2LMHeadModel"
 
12
  "attn_pdrop": 0.1,
13
  "bad_words_ids": null,
14
  "begin_suppress_tokens": null,
15
+ "bos_token_id": 50256,
16
  "chunk_size_feed_forward": 0,
17
  "cross_attention_hidden_size": null,
18
  "decoder_start_token_id": null,
 
21
  "early_stopping": false,
22
  "embd_pdrop": 0.1,
23
  "encoder_no_repeat_ngram_size": 0,
24
+ "eos_token_id": 50256,
25
  "exponential_decay_length_penalty": null,
26
  "finetuning_task": null,
27
  "forced_bos_token_id": null,
28
  "forced_eos_token_id": null,
 
29
  "id2label": {
30
  "0": "LABEL_0",
31
  "1": "LABEL_1"
 
43
  "min_length": 0,
44
  "model_type": "gpt2",
45
  "n_ctx": 1024,
46
+ "n_embd": 768,
47
+ "n_head": 12,
48
  "n_inner": null,
49
+ "n_layer": 12,
50
  "n_positions": 1024,
51
  "no_repeat_ngram_size": 0,
52
  "num_beam_groups": 1,
 
77
  "task_specific_params": {
78
  "text-generation": {
79
  "do_sample": true,
80
+ "max_length": 50
81
  }
82
  },
83
  "temperature": 1.0,
 
92
  "typical_p": 1.0,
93
  "use_bfloat16": false,
94
  "use_cache": true,
95
+ "vocab_size": 50257
96
  },
97
  "decoder_start_token_id": 0,
98
  "encoder": {
 
255
  "vocab_size": 32,
256
  "xvector_output_dim": 512
257
  },
258
+ "eos_token_id": 50256,
259
  "is_encoder_decoder": true,
260
  "model_type": "speech-encoder-decoder",
261
  "pad_token_id": 0,
merges.txt CHANGED
The diff for this file is too large to render. See raw diff
 
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0bf3722144ebd79ab0e7c35f900d6350e3238e503f924e0f68d552374295d2d9
3
- size 550862672
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:792d61b4d96cc627eb7b0434406c45aa85c2ea855b4663b26630315ad46af14d
3
+ size 988766816
special_tokens_map.json CHANGED
@@ -2,14 +2,14 @@
2
  "bos_token": {
3
  "content": "<|endoftext|>",
4
  "lstrip": false,
5
- "normalized": true,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
  "content": "<|endoftext|>",
11
  "lstrip": false,
12
- "normalized": true,
13
  "rstrip": false,
14
  "single_word": false
15
  },
@@ -17,7 +17,7 @@
17
  "unk_token": {
18
  "content": "<|endoftext|>",
19
  "lstrip": false,
20
- "normalized": true,
21
  "rstrip": false,
22
  "single_word": false
23
  }
 
2
  "bos_token": {
3
  "content": "<|endoftext|>",
4
  "lstrip": false,
5
+ "normalized": false,
6
  "rstrip": false,
7
  "single_word": false
8
  },
9
  "eos_token": {
10
  "content": "<|endoftext|>",
11
  "lstrip": false,
12
+ "normalized": false,
13
  "rstrip": false,
14
  "single_word": false
15
  },
 
17
  "unk_token": {
18
  "content": "<|endoftext|>",
19
  "lstrip": false,
20
+ "normalized": false,
21
  "rstrip": false,
22
  "single_word": false
23
  }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json CHANGED
@@ -1,11 +1,10 @@
1
  {
2
- "add_bos_token": false,
3
  "add_prefix_space": false,
4
  "added_tokens_decoder": {
5
  "0": {
6
  "content": "<|endoftext|>",
7
  "lstrip": false,
8
- "normalized": true,
9
  "rstrip": false,
10
  "single_word": false,
11
  "special": true
 
1
  {
 
2
  "add_prefix_space": false,
3
  "added_tokens_decoder": {
4
  "0": {
5
  "content": "<|endoftext|>",
6
  "lstrip": false,
7
+ "normalized": false,
8
  "rstrip": false,
9
  "single_word": false,
10
  "special": true
vocab.json CHANGED
The diff for this file is too large to render. See raw diff