prince-canuma commited on
Commit
3ae62e2
·
verified ·
1 Parent(s): d1e7494

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
BiCodec/config.yaml ADDED
@@ -0,0 +1,60 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ audio_tokenizer:
2
+ mel_params:
3
+ sample_rate: 16000
4
+ n_fft: 1024
5
+ win_length: 640
6
+ hop_length: 320
7
+ mel_fmin: 10
8
+ mel_fmax: null
9
+ num_mels: 128
10
+
11
+ encoder:
12
+ input_channels: 1024
13
+ vocos_dim: 384
14
+ vocos_intermediate_dim: 2048
15
+ vocos_num_layers: 12
16
+ out_channels: 1024
17
+ sample_ratios: [1,1]
18
+
19
+ decoder:
20
+ input_channel: 1024
21
+ channels: 1536
22
+ rates: [8, 5, 4, 2]
23
+ kernel_sizes: [16,11,8,4]
24
+
25
+ quantizer:
26
+ input_dim: 1024
27
+ codebook_size: 8192
28
+ codebook_dim: 8
29
+ commitment: 0.25
30
+ codebook_loss_weight: 2.0
31
+ use_l2_normlize: True
32
+ threshold_ema_dead_code: 0.2
33
+
34
+ speaker_encoder:
35
+ input_dim: 128
36
+ out_dim: 1024
37
+ latent_dim: 128
38
+ token_num: 32
39
+ fsq_levels: [4, 4, 4, 4, 4, 4]
40
+ fsq_num_quantizers: 1
41
+
42
+ prenet:
43
+ input_channels: 1024
44
+ vocos_dim: 384
45
+ vocos_intermediate_dim: 2048
46
+ vocos_num_layers: 12
47
+ out_channels: 1024
48
+ condition_dim: 1024
49
+ sample_ratios: [1,1]
50
+ use_tanh_at_final: False
51
+
52
+ postnet:
53
+ input_channels: 1024
54
+ vocos_dim: 384
55
+ vocos_intermediate_dim: 2048
56
+ vocos_num_layers: 6
57
+ out_channels: 1024
58
+ use_tanh_at_final: False
59
+
60
+
BiCodec/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9940cd48d4446e4340ced82d234bf5618350dd9f5db900ebe47a4fdb03867ec
3
+ size 625518756
README.md ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: cc-by-nc-sa-4.0
3
+ language:
4
+ - en
5
+ - zh
6
+ tags:
7
+ - text-to-speech
8
+ - mlx
9
+ library_tag: spark-tts
10
+ ---
11
+
12
+ # mlx-community/Spark-TTS-0.5B-fp16
13
+ This model was converted to MLX format from [`prince-canuma/Spark-TTS-0.5B`](https://huggingface.co/prince-canuma/Spark-TTS-0.5B) using mlx-audio version **0.2.0**.
14
+ Refer to the [original model card](https://huggingface.co/prince-canuma/Spark-TTS-0.5B) for more details on the model.
15
+ ## Use with mlx
16
+
17
+ ```bash
18
+ pip install -U mlx-audio
19
+ ```
20
+
21
+ ```bash
22
+ python -m mlx_audio.tts.generate --model mlx-community/Spark-TTS-0.5B-fp16 --text "Describe this image."
23
+ ```
added_tokens.json ADDED
The diff for this file is too large to render. See raw diff
 
audio_tokenizer_config.yaml ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ highpass_cutoff_freq: 40
2
+ sample_rate: 16000
3
+ segment_duration: 2.4 # (s)
4
+ max_val_duration: 12 # (s)
5
+ latent_hop_length: 320
6
+ ref_segment_duration: 6
7
+ volume_normalize: true
config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_attn_implementation_autoset": false,
3
+ "add_cross_attention": false,
4
+ "architectures": [
5
+ "Qwen2ForCausalLM"
6
+ ],
7
+ "attention_dropout": 0.0,
8
+ "bad_words_ids": null,
9
+ "begin_suppress_tokens": null,
10
+ "bos_token_id": 151643,
11
+ "chunk_size_feed_forward": 0,
12
+ "cross_attention_hidden_size": null,
13
+ "decoder_start_token_id": null,
14
+ "diversity_penalty": 0.0,
15
+ "do_sample": false,
16
+ "early_stopping": false,
17
+ "encoder_no_repeat_ngram_size": 0,
18
+ "eos_token_id": 151645,
19
+ "exponential_decay_length_penalty": null,
20
+ "finetuning_task": null,
21
+ "forced_bos_token_id": null,
22
+ "forced_eos_token_id": null,
23
+ "hidden_act": "silu",
24
+ "hidden_size": 896,
25
+ "id2label": {
26
+ "0": "LABEL_0",
27
+ "1": "LABEL_1"
28
+ },
29
+ "initializer_range": 0.02,
30
+ "intermediate_size": 4864,
31
+ "is_decoder": false,
32
+ "is_encoder_decoder": false,
33
+ "label2id": {
34
+ "LABEL_0": 0,
35
+ "LABEL_1": 1
36
+ },
37
+ "length_penalty": 1.0,
38
+ "max_length": 20,
39
+ "max_position_embeddings": 32768,
40
+ "max_window_layers": 21,
41
+ "min_length": 0,
42
+ "model_type": "qwen2",
43
+ "no_repeat_ngram_size": 0,
44
+ "num_attention_heads": 14,
45
+ "num_beam_groups": 1,
46
+ "num_beams": 1,
47
+ "num_hidden_layers": 24,
48
+ "num_key_value_heads": 2,
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
+ "rms_norm_eps": 1e-06,
62
+ "rope_scaling": null,
63
+ "rope_theta": 1000000.0,
64
+ "sep_token_id": null,
65
+ "sliding_window": 32768,
66
+ "suppress_tokens": null,
67
+ "task_specific_params": null,
68
+ "temperature": 1.0,
69
+ "tf_legacy_loss": false,
70
+ "tie_encoder_decoder": false,
71
+ "tie_word_embeddings": true,
72
+ "tokenizer_class": null,
73
+ "top_k": 50,
74
+ "top_p": 1.0,
75
+ "torch_dtype": "bfloat16",
76
+ "torchscript": false,
77
+ "transformers_version": "4.51.3",
78
+ "typical_p": 1.0,
79
+ "use_bfloat16": false,
80
+ "use_cache": true,
81
+ "use_sliding_window": false,
82
+ "vocab_size": 166000
83
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1861b1be28c9d6d16f56bdc36948e0d3e4e2c74d1d358784086e41abe463b091
3
+ size 1013300153
model.safetensors.index.json ADDED
@@ -0,0 +1,297 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 1013268224
4
+ },
5
+ "weight_map": {
6
+ "model.embed_tokens.weight": "model.safetensors",
7
+ "model.layers.0.input_layernorm.weight": "model.safetensors",
8
+ "model.layers.0.mlp.down_proj.weight": "model.safetensors",
9
+ "model.layers.0.mlp.gate_proj.weight": "model.safetensors",
10
+ "model.layers.0.mlp.up_proj.weight": "model.safetensors",
11
+ "model.layers.0.post_attention_layernorm.weight": "model.safetensors",
12
+ "model.layers.0.self_attn.k_proj.bias": "model.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model.safetensors",
15
+ "model.layers.0.self_attn.q_proj.bias": "model.safetensors",
16
+ "model.layers.0.self_attn.q_proj.weight": "model.safetensors",
17
+ "model.layers.0.self_attn.v_proj.bias": "model.safetensors",
18
+ "model.layers.0.self_attn.v_proj.weight": "model.safetensors",
19
+ "model.layers.1.input_layernorm.weight": "model.safetensors",
20
+ "model.layers.1.mlp.down_proj.weight": "model.safetensors",
21
+ "model.layers.1.mlp.gate_proj.weight": "model.safetensors",
22
+ "model.layers.1.mlp.up_proj.weight": "model.safetensors",
23
+ "model.layers.1.post_attention_layernorm.weight": "model.safetensors",
24
+ "model.layers.1.self_attn.k_proj.bias": "model.safetensors",
25
+ "model.layers.1.self_attn.k_proj.weight": "model.safetensors",
26
+ "model.layers.1.self_attn.o_proj.weight": "model.safetensors",
27
+ "model.layers.1.self_attn.q_proj.bias": "model.safetensors",
28
+ "model.layers.1.self_attn.q_proj.weight": "model.safetensors",
29
+ "model.layers.1.self_attn.v_proj.bias": "model.safetensors",
30
+ "model.layers.1.self_attn.v_proj.weight": "model.safetensors",
31
+ "model.layers.10.input_layernorm.weight": "model.safetensors",
32
+ "model.layers.10.mlp.down_proj.weight": "model.safetensors",
33
+ "model.layers.10.mlp.gate_proj.weight": "model.safetensors",
34
+ "model.layers.10.mlp.up_proj.weight": "model.safetensors",
35
+ "model.layers.10.post_attention_layernorm.weight": "model.safetensors",
36
+ "model.layers.10.self_attn.k_proj.bias": "model.safetensors",
37
+ "model.layers.10.self_attn.k_proj.weight": "model.safetensors",
38
+ "model.layers.10.self_attn.o_proj.weight": "model.safetensors",
39
+ "model.layers.10.self_attn.q_proj.bias": "model.safetensors",
40
+ "model.layers.10.self_attn.q_proj.weight": "model.safetensors",
41
+ "model.layers.10.self_attn.v_proj.bias": "model.safetensors",
42
+ "model.layers.10.self_attn.v_proj.weight": "model.safetensors",
43
+ "model.layers.11.input_layernorm.weight": "model.safetensors",
44
+ "model.layers.11.mlp.down_proj.weight": "model.safetensors",
45
+ "model.layers.11.mlp.gate_proj.weight": "model.safetensors",
46
+ "model.layers.11.mlp.up_proj.weight": "model.safetensors",
47
+ "model.layers.11.post_attention_layernorm.weight": "model.safetensors",
48
+ "model.layers.11.self_attn.k_proj.bias": "model.safetensors",
49
+ "model.layers.11.self_attn.k_proj.weight": "model.safetensors",
50
+ "model.layers.11.self_attn.o_proj.weight": "model.safetensors",
51
+ "model.layers.11.self_attn.q_proj.bias": "model.safetensors",
52
+ "model.layers.11.self_attn.q_proj.weight": "model.safetensors",
53
+ "model.layers.11.self_attn.v_proj.bias": "model.safetensors",
54
+ "model.layers.11.self_attn.v_proj.weight": "model.safetensors",
55
+ "model.layers.12.input_layernorm.weight": "model.safetensors",
56
+ "model.layers.12.mlp.down_proj.weight": "model.safetensors",
57
+ "model.layers.12.mlp.gate_proj.weight": "model.safetensors",
58
+ "model.layers.12.mlp.up_proj.weight": "model.safetensors",
59
+ "model.layers.12.post_attention_layernorm.weight": "model.safetensors",
60
+ "model.layers.12.self_attn.k_proj.bias": "model.safetensors",
61
+ "model.layers.12.self_attn.k_proj.weight": "model.safetensors",
62
+ "model.layers.12.self_attn.o_proj.weight": "model.safetensors",
63
+ "model.layers.12.self_attn.q_proj.bias": "model.safetensors",
64
+ "model.layers.12.self_attn.q_proj.weight": "model.safetensors",
65
+ "model.layers.12.self_attn.v_proj.bias": "model.safetensors",
66
+ "model.layers.12.self_attn.v_proj.weight": "model.safetensors",
67
+ "model.layers.13.input_layernorm.weight": "model.safetensors",
68
+ "model.layers.13.mlp.down_proj.weight": "model.safetensors",
69
+ "model.layers.13.mlp.gate_proj.weight": "model.safetensors",
70
+ "model.layers.13.mlp.up_proj.weight": "model.safetensors",
71
+ "model.layers.13.post_attention_layernorm.weight": "model.safetensors",
72
+ "model.layers.13.self_attn.k_proj.bias": "model.safetensors",
73
+ "model.layers.13.self_attn.k_proj.weight": "model.safetensors",
74
+ "model.layers.13.self_attn.o_proj.weight": "model.safetensors",
75
+ "model.layers.13.self_attn.q_proj.bias": "model.safetensors",
76
+ "model.layers.13.self_attn.q_proj.weight": "model.safetensors",
77
+ "model.layers.13.self_attn.v_proj.bias": "model.safetensors",
78
+ "model.layers.13.self_attn.v_proj.weight": "model.safetensors",
79
+ "model.layers.14.input_layernorm.weight": "model.safetensors",
80
+ "model.layers.14.mlp.down_proj.weight": "model.safetensors",
81
+ "model.layers.14.mlp.gate_proj.weight": "model.safetensors",
82
+ "model.layers.14.mlp.up_proj.weight": "model.safetensors",
83
+ "model.layers.14.post_attention_layernorm.weight": "model.safetensors",
84
+ "model.layers.14.self_attn.k_proj.bias": "model.safetensors",
85
+ "model.layers.14.self_attn.k_proj.weight": "model.safetensors",
86
+ "model.layers.14.self_attn.o_proj.weight": "model.safetensors",
87
+ "model.layers.14.self_attn.q_proj.bias": "model.safetensors",
88
+ "model.layers.14.self_attn.q_proj.weight": "model.safetensors",
89
+ "model.layers.14.self_attn.v_proj.bias": "model.safetensors",
90
+ "model.layers.14.self_attn.v_proj.weight": "model.safetensors",
91
+ "model.layers.15.input_layernorm.weight": "model.safetensors",
92
+ "model.layers.15.mlp.down_proj.weight": "model.safetensors",
93
+ "model.layers.15.mlp.gate_proj.weight": "model.safetensors",
94
+ "model.layers.15.mlp.up_proj.weight": "model.safetensors",
95
+ "model.layers.15.post_attention_layernorm.weight": "model.safetensors",
96
+ "model.layers.15.self_attn.k_proj.bias": "model.safetensors",
97
+ "model.layers.15.self_attn.k_proj.weight": "model.safetensors",
98
+ "model.layers.15.self_attn.o_proj.weight": "model.safetensors",
99
+ "model.layers.15.self_attn.q_proj.bias": "model.safetensors",
100
+ "model.layers.15.self_attn.q_proj.weight": "model.safetensors",
101
+ "model.layers.15.self_attn.v_proj.bias": "model.safetensors",
102
+ "model.layers.15.self_attn.v_proj.weight": "model.safetensors",
103
+ "model.layers.16.input_layernorm.weight": "model.safetensors",
104
+ "model.layers.16.mlp.down_proj.weight": "model.safetensors",
105
+ "model.layers.16.mlp.gate_proj.weight": "model.safetensors",
106
+ "model.layers.16.mlp.up_proj.weight": "model.safetensors",
107
+ "model.layers.16.post_attention_layernorm.weight": "model.safetensors",
108
+ "model.layers.16.self_attn.k_proj.bias": "model.safetensors",
109
+ "model.layers.16.self_attn.k_proj.weight": "model.safetensors",
110
+ "model.layers.16.self_attn.o_proj.weight": "model.safetensors",
111
+ "model.layers.16.self_attn.q_proj.bias": "model.safetensors",
112
+ "model.layers.16.self_attn.q_proj.weight": "model.safetensors",
113
+ "model.layers.16.self_attn.v_proj.bias": "model.safetensors",
114
+ "model.layers.16.self_attn.v_proj.weight": "model.safetensors",
115
+ "model.layers.17.input_layernorm.weight": "model.safetensors",
116
+ "model.layers.17.mlp.down_proj.weight": "model.safetensors",
117
+ "model.layers.17.mlp.gate_proj.weight": "model.safetensors",
118
+ "model.layers.17.mlp.up_proj.weight": "model.safetensors",
119
+ "model.layers.17.post_attention_layernorm.weight": "model.safetensors",
120
+ "model.layers.17.self_attn.k_proj.bias": "model.safetensors",
121
+ "model.layers.17.self_attn.k_proj.weight": "model.safetensors",
122
+ "model.layers.17.self_attn.o_proj.weight": "model.safetensors",
123
+ "model.layers.17.self_attn.q_proj.bias": "model.safetensors",
124
+ "model.layers.17.self_attn.q_proj.weight": "model.safetensors",
125
+ "model.layers.17.self_attn.v_proj.bias": "model.safetensors",
126
+ "model.layers.17.self_attn.v_proj.weight": "model.safetensors",
127
+ "model.layers.18.input_layernorm.weight": "model.safetensors",
128
+ "model.layers.18.mlp.down_proj.weight": "model.safetensors",
129
+ "model.layers.18.mlp.gate_proj.weight": "model.safetensors",
130
+ "model.layers.18.mlp.up_proj.weight": "model.safetensors",
131
+ "model.layers.18.post_attention_layernorm.weight": "model.safetensors",
132
+ "model.layers.18.self_attn.k_proj.bias": "model.safetensors",
133
+ "model.layers.18.self_attn.k_proj.weight": "model.safetensors",
134
+ "model.layers.18.self_attn.o_proj.weight": "model.safetensors",
135
+ "model.layers.18.self_attn.q_proj.bias": "model.safetensors",
136
+ "model.layers.18.self_attn.q_proj.weight": "model.safetensors",
137
+ "model.layers.18.self_attn.v_proj.bias": "model.safetensors",
138
+ "model.layers.18.self_attn.v_proj.weight": "model.safetensors",
139
+ "model.layers.19.input_layernorm.weight": "model.safetensors",
140
+ "model.layers.19.mlp.down_proj.weight": "model.safetensors",
141
+ "model.layers.19.mlp.gate_proj.weight": "model.safetensors",
142
+ "model.layers.19.mlp.up_proj.weight": "model.safetensors",
143
+ "model.layers.19.post_attention_layernorm.weight": "model.safetensors",
144
+ "model.layers.19.self_attn.k_proj.bias": "model.safetensors",
145
+ "model.layers.19.self_attn.k_proj.weight": "model.safetensors",
146
+ "model.layers.19.self_attn.o_proj.weight": "model.safetensors",
147
+ "model.layers.19.self_attn.q_proj.bias": "model.safetensors",
148
+ "model.layers.19.self_attn.q_proj.weight": "model.safetensors",
149
+ "model.layers.19.self_attn.v_proj.bias": "model.safetensors",
150
+ "model.layers.19.self_attn.v_proj.weight": "model.safetensors",
151
+ "model.layers.2.input_layernorm.weight": "model.safetensors",
152
+ "model.layers.2.mlp.down_proj.weight": "model.safetensors",
153
+ "model.layers.2.mlp.gate_proj.weight": "model.safetensors",
154
+ "model.layers.2.mlp.up_proj.weight": "model.safetensors",
155
+ "model.layers.2.post_attention_layernorm.weight": "model.safetensors",
156
+ "model.layers.2.self_attn.k_proj.bias": "model.safetensors",
157
+ "model.layers.2.self_attn.k_proj.weight": "model.safetensors",
158
+ "model.layers.2.self_attn.o_proj.weight": "model.safetensors",
159
+ "model.layers.2.self_attn.q_proj.bias": "model.safetensors",
160
+ "model.layers.2.self_attn.q_proj.weight": "model.safetensors",
161
+ "model.layers.2.self_attn.v_proj.bias": "model.safetensors",
162
+ "model.layers.2.self_attn.v_proj.weight": "model.safetensors",
163
+ "model.layers.20.input_layernorm.weight": "model.safetensors",
164
+ "model.layers.20.mlp.down_proj.weight": "model.safetensors",
165
+ "model.layers.20.mlp.gate_proj.weight": "model.safetensors",
166
+ "model.layers.20.mlp.up_proj.weight": "model.safetensors",
167
+ "model.layers.20.post_attention_layernorm.weight": "model.safetensors",
168
+ "model.layers.20.self_attn.k_proj.bias": "model.safetensors",
169
+ "model.layers.20.self_attn.k_proj.weight": "model.safetensors",
170
+ "model.layers.20.self_attn.o_proj.weight": "model.safetensors",
171
+ "model.layers.20.self_attn.q_proj.bias": "model.safetensors",
172
+ "model.layers.20.self_attn.q_proj.weight": "model.safetensors",
173
+ "model.layers.20.self_attn.v_proj.bias": "model.safetensors",
174
+ "model.layers.20.self_attn.v_proj.weight": "model.safetensors",
175
+ "model.layers.21.input_layernorm.weight": "model.safetensors",
176
+ "model.layers.21.mlp.down_proj.weight": "model.safetensors",
177
+ "model.layers.21.mlp.gate_proj.weight": "model.safetensors",
178
+ "model.layers.21.mlp.up_proj.weight": "model.safetensors",
179
+ "model.layers.21.post_attention_layernorm.weight": "model.safetensors",
180
+ "model.layers.21.self_attn.k_proj.bias": "model.safetensors",
181
+ "model.layers.21.self_attn.k_proj.weight": "model.safetensors",
182
+ "model.layers.21.self_attn.o_proj.weight": "model.safetensors",
183
+ "model.layers.21.self_attn.q_proj.bias": "model.safetensors",
184
+ "model.layers.21.self_attn.q_proj.weight": "model.safetensors",
185
+ "model.layers.21.self_attn.v_proj.bias": "model.safetensors",
186
+ "model.layers.21.self_attn.v_proj.weight": "model.safetensors",
187
+ "model.layers.22.input_layernorm.weight": "model.safetensors",
188
+ "model.layers.22.mlp.down_proj.weight": "model.safetensors",
189
+ "model.layers.22.mlp.gate_proj.weight": "model.safetensors",
190
+ "model.layers.22.mlp.up_proj.weight": "model.safetensors",
191
+ "model.layers.22.post_attention_layernorm.weight": "model.safetensors",
192
+ "model.layers.22.self_attn.k_proj.bias": "model.safetensors",
193
+ "model.layers.22.self_attn.k_proj.weight": "model.safetensors",
194
+ "model.layers.22.self_attn.o_proj.weight": "model.safetensors",
195
+ "model.layers.22.self_attn.q_proj.bias": "model.safetensors",
196
+ "model.layers.22.self_attn.q_proj.weight": "model.safetensors",
197
+ "model.layers.22.self_attn.v_proj.bias": "model.safetensors",
198
+ "model.layers.22.self_attn.v_proj.weight": "model.safetensors",
199
+ "model.layers.23.input_layernorm.weight": "model.safetensors",
200
+ "model.layers.23.mlp.down_proj.weight": "model.safetensors",
201
+ "model.layers.23.mlp.gate_proj.weight": "model.safetensors",
202
+ "model.layers.23.mlp.up_proj.weight": "model.safetensors",
203
+ "model.layers.23.post_attention_layernorm.weight": "model.safetensors",
204
+ "model.layers.23.self_attn.k_proj.bias": "model.safetensors",
205
+ "model.layers.23.self_attn.k_proj.weight": "model.safetensors",
206
+ "model.layers.23.self_attn.o_proj.weight": "model.safetensors",
207
+ "model.layers.23.self_attn.q_proj.bias": "model.safetensors",
208
+ "model.layers.23.self_attn.q_proj.weight": "model.safetensors",
209
+ "model.layers.23.self_attn.v_proj.bias": "model.safetensors",
210
+ "model.layers.23.self_attn.v_proj.weight": "model.safetensors",
211
+ "model.layers.3.input_layernorm.weight": "model.safetensors",
212
+ "model.layers.3.mlp.down_proj.weight": "model.safetensors",
213
+ "model.layers.3.mlp.gate_proj.weight": "model.safetensors",
214
+ "model.layers.3.mlp.up_proj.weight": "model.safetensors",
215
+ "model.layers.3.post_attention_layernorm.weight": "model.safetensors",
216
+ "model.layers.3.self_attn.k_proj.bias": "model.safetensors",
217
+ "model.layers.3.self_attn.k_proj.weight": "model.safetensors",
218
+ "model.layers.3.self_attn.o_proj.weight": "model.safetensors",
219
+ "model.layers.3.self_attn.q_proj.bias": "model.safetensors",
220
+ "model.layers.3.self_attn.q_proj.weight": "model.safetensors",
221
+ "model.layers.3.self_attn.v_proj.bias": "model.safetensors",
222
+ "model.layers.3.self_attn.v_proj.weight": "model.safetensors",
223
+ "model.layers.4.input_layernorm.weight": "model.safetensors",
224
+ "model.layers.4.mlp.down_proj.weight": "model.safetensors",
225
+ "model.layers.4.mlp.gate_proj.weight": "model.safetensors",
226
+ "model.layers.4.mlp.up_proj.weight": "model.safetensors",
227
+ "model.layers.4.post_attention_layernorm.weight": "model.safetensors",
228
+ "model.layers.4.self_attn.k_proj.bias": "model.safetensors",
229
+ "model.layers.4.self_attn.k_proj.weight": "model.safetensors",
230
+ "model.layers.4.self_attn.o_proj.weight": "model.safetensors",
231
+ "model.layers.4.self_attn.q_proj.bias": "model.safetensors",
232
+ "model.layers.4.self_attn.q_proj.weight": "model.safetensors",
233
+ "model.layers.4.self_attn.v_proj.bias": "model.safetensors",
234
+ "model.layers.4.self_attn.v_proj.weight": "model.safetensors",
235
+ "model.layers.5.input_layernorm.weight": "model.safetensors",
236
+ "model.layers.5.mlp.down_proj.weight": "model.safetensors",
237
+ "model.layers.5.mlp.gate_proj.weight": "model.safetensors",
238
+ "model.layers.5.mlp.up_proj.weight": "model.safetensors",
239
+ "model.layers.5.post_attention_layernorm.weight": "model.safetensors",
240
+ "model.layers.5.self_attn.k_proj.bias": "model.safetensors",
241
+ "model.layers.5.self_attn.k_proj.weight": "model.safetensors",
242
+ "model.layers.5.self_attn.o_proj.weight": "model.safetensors",
243
+ "model.layers.5.self_attn.q_proj.bias": "model.safetensors",
244
+ "model.layers.5.self_attn.q_proj.weight": "model.safetensors",
245
+ "model.layers.5.self_attn.v_proj.bias": "model.safetensors",
246
+ "model.layers.5.self_attn.v_proj.weight": "model.safetensors",
247
+ "model.layers.6.input_layernorm.weight": "model.safetensors",
248
+ "model.layers.6.mlp.down_proj.weight": "model.safetensors",
249
+ "model.layers.6.mlp.gate_proj.weight": "model.safetensors",
250
+ "model.layers.6.mlp.up_proj.weight": "model.safetensors",
251
+ "model.layers.6.post_attention_layernorm.weight": "model.safetensors",
252
+ "model.layers.6.self_attn.k_proj.bias": "model.safetensors",
253
+ "model.layers.6.self_attn.k_proj.weight": "model.safetensors",
254
+ "model.layers.6.self_attn.o_proj.weight": "model.safetensors",
255
+ "model.layers.6.self_attn.q_proj.bias": "model.safetensors",
256
+ "model.layers.6.self_attn.q_proj.weight": "model.safetensors",
257
+ "model.layers.6.self_attn.v_proj.bias": "model.safetensors",
258
+ "model.layers.6.self_attn.v_proj.weight": "model.safetensors",
259
+ "model.layers.7.input_layernorm.weight": "model.safetensors",
260
+ "model.layers.7.mlp.down_proj.weight": "model.safetensors",
261
+ "model.layers.7.mlp.gate_proj.weight": "model.safetensors",
262
+ "model.layers.7.mlp.up_proj.weight": "model.safetensors",
263
+ "model.layers.7.post_attention_layernorm.weight": "model.safetensors",
264
+ "model.layers.7.self_attn.k_proj.bias": "model.safetensors",
265
+ "model.layers.7.self_attn.k_proj.weight": "model.safetensors",
266
+ "model.layers.7.self_attn.o_proj.weight": "model.safetensors",
267
+ "model.layers.7.self_attn.q_proj.bias": "model.safetensors",
268
+ "model.layers.7.self_attn.q_proj.weight": "model.safetensors",
269
+ "model.layers.7.self_attn.v_proj.bias": "model.safetensors",
270
+ "model.layers.7.self_attn.v_proj.weight": "model.safetensors",
271
+ "model.layers.8.input_layernorm.weight": "model.safetensors",
272
+ "model.layers.8.mlp.down_proj.weight": "model.safetensors",
273
+ "model.layers.8.mlp.gate_proj.weight": "model.safetensors",
274
+ "model.layers.8.mlp.up_proj.weight": "model.safetensors",
275
+ "model.layers.8.post_attention_layernorm.weight": "model.safetensors",
276
+ "model.layers.8.self_attn.k_proj.bias": "model.safetensors",
277
+ "model.layers.8.self_attn.k_proj.weight": "model.safetensors",
278
+ "model.layers.8.self_attn.o_proj.weight": "model.safetensors",
279
+ "model.layers.8.self_attn.q_proj.bias": "model.safetensors",
280
+ "model.layers.8.self_attn.q_proj.weight": "model.safetensors",
281
+ "model.layers.8.self_attn.v_proj.bias": "model.safetensors",
282
+ "model.layers.8.self_attn.v_proj.weight": "model.safetensors",
283
+ "model.layers.9.input_layernorm.weight": "model.safetensors",
284
+ "model.layers.9.mlp.down_proj.weight": "model.safetensors",
285
+ "model.layers.9.mlp.gate_proj.weight": "model.safetensors",
286
+ "model.layers.9.mlp.up_proj.weight": "model.safetensors",
287
+ "model.layers.9.post_attention_layernorm.weight": "model.safetensors",
288
+ "model.layers.9.self_attn.k_proj.bias": "model.safetensors",
289
+ "model.layers.9.self_attn.k_proj.weight": "model.safetensors",
290
+ "model.layers.9.self_attn.o_proj.weight": "model.safetensors",
291
+ "model.layers.9.self_attn.q_proj.bias": "model.safetensors",
292
+ "model.layers.9.self_attn.q_proj.weight": "model.safetensors",
293
+ "model.layers.9.self_attn.v_proj.bias": "model.safetensors",
294
+ "model.layers.9.self_attn.v_proj.weight": "model.safetensors",
295
+ "model.norm.weight": "model.safetensors"
296
+ }
297
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8b057d6ca205a429cc3428b9fc815f0d6ee1d53106dd5e5b129ef9db2ff057
3
+ size 14129172
tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
wav2vec2-large-xlsr-53/config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_dropout": 0.0,
3
+ "apply_spec_augment": true,
4
+ "architectures": [
5
+ "Wav2Vec2ForPreTraining"
6
+ ],
7
+ "attention_dropout": 0.1,
8
+ "bos_token_id": 1,
9
+ "codevector_dim": 768,
10
+ "contrastive_logits_temperature": 0.1,
11
+ "conv_bias": true,
12
+ "conv_dim": [
13
+ 512,
14
+ 512,
15
+ 512,
16
+ 512,
17
+ 512,
18
+ 512,
19
+ 512
20
+ ],
21
+ "conv_kernel": [
22
+ 10,
23
+ 3,
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 2,
28
+ 2
29
+ ],
30
+ "conv_stride": [
31
+ 5,
32
+ 2,
33
+ 2,
34
+ 2,
35
+ 2,
36
+ 2,
37
+ 2
38
+ ],
39
+ "ctc_loss_reduction": "sum",
40
+ "ctc_zero_infinity": false,
41
+ "diversity_loss_weight": 0.1,
42
+ "do_stable_layer_norm": true,
43
+ "eos_token_id": 2,
44
+ "feat_extract_activation": "gelu",
45
+ "feat_extract_dropout": 0.0,
46
+ "feat_extract_norm": "layer",
47
+ "feat_proj_dropout": 0.1,
48
+ "feat_quantizer_dropout": 0.0,
49
+ "final_dropout": 0.0,
50
+ "gradient_checkpointing": false,
51
+ "hidden_act": "gelu",
52
+ "hidden_dropout": 0.1,
53
+ "hidden_size": 1024,
54
+ "initializer_range": 0.02,
55
+ "intermediate_size": 4096,
56
+ "layer_norm_eps": 1e-05,
57
+ "layerdrop": 0.1,
58
+ "mask_channel_length": 10,
59
+ "mask_channel_min_space": 1,
60
+ "mask_channel_other": 0.0,
61
+ "mask_channel_prob": 0.0,
62
+ "mask_channel_selection": "static",
63
+ "mask_feature_length": 10,
64
+ "mask_feature_prob": 0.0,
65
+ "mask_time_length": 10,
66
+ "mask_time_min_space": 1,
67
+ "mask_time_other": 0.0,
68
+ "mask_time_prob": 0.075,
69
+ "mask_time_selection": "static",
70
+ "model_type": "wav2vec2",
71
+ "num_attention_heads": 16,
72
+ "num_codevector_groups": 2,
73
+ "num_codevectors_per_group": 320,
74
+ "num_conv_pos_embedding_groups": 16,
75
+ "num_conv_pos_embeddings": 128,
76
+ "num_feat_extract_layers": 7,
77
+ "num_hidden_layers": 24,
78
+ "num_negatives": 100,
79
+ "pad_token_id": 0,
80
+ "proj_codevector_dim": 768,
81
+ "transformers_version": "4.7.0.dev0",
82
+ "vocab_size": 32
83
+ }
wav2vec2-large-xlsr-53/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a8b60ccc08ffcd555abc1df8e113228b9956e855034f4287d8c4ab7ae8b53ba
3
+ size 1261803488
wav2vec2-large-xlsr-53/preprocessor_config.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_normalize": true,
3
+ "feature_extractor_type": "Wav2Vec2FeatureExtractor",
4
+ "feature_size": 1,
5
+ "padding_side": "right",
6
+ "padding_value": 0,
7
+ "return_attention_mask": true,
8
+ "sampling_rate": 16000
9
+ }