Upload folder using huggingface_hub
Browse files- config.json +22 -0
- model.safetensors +3 -0
- preprocessor_config.json +14 -0
config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"activation_dropout": 0.0,
|
| 3 |
+
"activation_function": "gelu",
|
| 4 |
+
"architectures": [
|
| 5 |
+
"Qwen2AudioEncoder"
|
| 6 |
+
],
|
| 7 |
+
"attention_dropout": 0.0,
|
| 8 |
+
"d_model": 1280,
|
| 9 |
+
"dropout": 0.0,
|
| 10 |
+
"encoder_attention_heads": 20,
|
| 11 |
+
"encoder_ffn_dim": 5120,
|
| 12 |
+
"encoder_layerdrop": 0.0,
|
| 13 |
+
"encoder_layers": 32,
|
| 14 |
+
"init_std": 0.02,
|
| 15 |
+
"max_source_positions": 1500,
|
| 16 |
+
"model_type": "qwen2_audio_encoder",
|
| 17 |
+
"num_hidden_layers": 32,
|
| 18 |
+
"num_mel_bins": 128,
|
| 19 |
+
"scale_embedding": false,
|
| 20 |
+
"torch_dtype": "bfloat16",
|
| 21 |
+
"transformers_version": "4.45.0"
|
| 22 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:846b51a72a33abfcfd5a53d94aed4db3e3aff559197b9713db3848387e5f879e
|
| 3 |
+
size 1273988176
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chunk_length": 30,
|
| 3 |
+
"feature_extractor_type": "WhisperFeatureExtractor",
|
| 4 |
+
"feature_size": 128,
|
| 5 |
+
"hop_length": 160,
|
| 6 |
+
"n_fft": 400,
|
| 7 |
+
"n_samples": 480000,
|
| 8 |
+
"nb_max_frames": 3000,
|
| 9 |
+
"padding_side": "right",
|
| 10 |
+
"padding_value": 0.0,
|
| 11 |
+
"processor_class": "Qwen2AudioProcessor",
|
| 12 |
+
"return_attention_mask": true,
|
| 13 |
+
"sampling_rate": 16000
|
| 14 |
+
}
|