Upload folder using huggingface_hub
Browse files- config.json +3 -3
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"OmniSpeech2SLlamaForCausalLM"
|
5 |
],
|
@@ -48,12 +48,12 @@
|
|
48 |
"rope_theta": 500000.0,
|
49 |
"special_tokens": 4,
|
50 |
"speech_bos_token_id": 6561,
|
51 |
-
"speech_encoder": "/
|
52 |
"speech_encoder_ds_rate": 5,
|
53 |
"speech_encoder_hidden_size": 1280,
|
54 |
"speech_encoder_type": "whisper",
|
55 |
"speech_eos_token_id": 6563,
|
56 |
-
"speech_generator_config": "
|
57 |
"speech_generator_type": "ar_mtp_v4",
|
58 |
"speech_max_position_embeddings": 2048,
|
59 |
"speech_padding_token_id": 6564,
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "./checkpoints/VocalNet-1B",
|
3 |
"architectures": [
|
4 |
"OmniSpeech2SLlamaForCausalLM"
|
5 |
],
|
|
|
48 |
"rope_theta": 500000.0,
|
49 |
"special_tokens": 4,
|
50 |
"speech_bos_token_id": 6561,
|
51 |
+
"speech_encoder": "./models/speech_encoder/whisper_large_v3",
|
52 |
"speech_encoder_ds_rate": 5,
|
53 |
"speech_encoder_hidden_size": 1280,
|
54 |
"speech_encoder_type": "whisper",
|
55 |
"speech_eos_token_id": 6563,
|
56 |
+
"speech_generator_config": "./scripts/mtp/ar_config_5.yaml",
|
57 |
"speech_generator_type": "ar_mtp_v4",
|
58 |
"speech_max_position_embeddings": 2048,
|
59 |
"speech_padding_token_id": 6564,
|