Text-to-Speech
Transformers
Safetensors
English
parler_tts
text2text-generation
annotation
ipsilondev commited on
Commit
78ea118
1 Parent(s): 664ad5a

removing audio encoder to test conversion of base model

Browse files
Files changed (1) hide show
  1. config.json +0 -70
config.json CHANGED
@@ -3,76 +3,6 @@
3
  "architectures": [
4
  "ParlerTTSForConditionalGeneration"
5
  ],
6
- "audio_encoder": {
7
- "_name_or_path": "ylacombe/dac_44khZ_8kbps",
8
- "add_cross_attention": false,
9
- "architectures": [
10
- "DACModel"
11
- ],
12
- "bad_words_ids": null,
13
- "begin_suppress_tokens": null,
14
- "bos_token_id": null,
15
- "chunk_size_feed_forward": 0,
16
- "codebook_size": 1024,
17
- "cross_attention_hidden_size": null,
18
- "decoder_start_token_id": null,
19
- "diversity_penalty": 0.0,
20
- "do_sample": false,
21
- "early_stopping": false,
22
- "encoder_no_repeat_ngram_size": 0,
23
- "eos_token_id": null,
24
- "exponential_decay_length_penalty": null,
25
- "finetuning_task": null,
26
- "forced_bos_token_id": null,
27
- "forced_eos_token_id": null,
28
- "frame_rate": 86,
29
- "id2label": {
30
- "0": "LABEL_0",
31
- "1": "LABEL_1"
32
- },
33
- "is_decoder": false,
34
- "is_encoder_decoder": false,
35
- "label2id": {
36
- "LABEL_0": 0,
37
- "LABEL_1": 1
38
- },
39
- "latent_dim": 1024,
40
- "length_penalty": 1.0,
41
- "max_length": 20,
42
- "min_length": 0,
43
- "model_bitrate": 8,
44
- "model_type": "dac",
45
- "no_repeat_ngram_size": 0,
46
- "num_beam_groups": 1,
47
- "num_beams": 1,
48
- "num_codebooks": 9,
49
- "num_return_sequences": 1,
50
- "output_attentions": false,
51
- "output_hidden_states": false,
52
- "output_scores": false,
53
- "pad_token_id": null,
54
- "prefix": null,
55
- "problem_type": null,
56
- "pruned_heads": {},
57
- "remove_invalid_values": false,
58
- "repetition_penalty": 1.0,
59
- "return_dict": true,
60
- "return_dict_in_generate": false,
61
- "sep_token_id": null,
62
- "suppress_tokens": null,
63
- "task_specific_params": null,
64
- "temperature": 1.0,
65
- "tf_legacy_loss": false,
66
- "tie_encoder_decoder": false,
67
- "tie_word_embeddings": true,
68
- "tokenizer_class": null,
69
- "top_k": 50,
70
- "top_p": 1.0,
71
- "torch_dtype": "float32",
72
- "torchscript": false,
73
- "typical_p": 1.0,
74
- "use_bfloat16": false
75
- },
76
  "decoder": {
77
  "_name_or_path": "/fsx/yoach/tmp/artefacts/decoder_400M/",
78
  "activation_dropout": 0.0,
 
3
  "architectures": [
4
  "ParlerTTSForConditionalGeneration"
5
  ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
6
  "decoder": {
7
  "_name_or_path": "/fsx/yoach/tmp/artefacts/decoder_400M/",
8
  "activation_dropout": 0.0,