Upload 6 files
Browse files- chat_template.jinja +2 -0
- preprocessor_config.json +14 -0
- processor_config.json +17 -0
- tokenizer.json +0 -0
- tokenizer_config.json +16 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,2 @@
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{% if message['role'] == 'user' %}USER: {{ message['content'] }}
|
| 2 |
+
ASSISTANT:{% elif message['role'] == 'assistant' %}{{ message['content'] }}{% endif %}{% endfor %}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"feature_extractor_type": "GraniteSpeechFeatureExtractor",
|
| 3 |
+
"melspec_kwargs": {
|
| 4 |
+
"hop_length": 160,
|
| 5 |
+
"n_fft": 512,
|
| 6 |
+
"n_mels": 80,
|
| 7 |
+
"sample_rate": 16000,
|
| 8 |
+
"win_length": 400
|
| 9 |
+
},
|
| 10 |
+
"processor_class": "GraniteSpeechProcessor",
|
| 11 |
+
"projector_downsample_rate": 5,
|
| 12 |
+
"projector_window_size": 15,
|
| 13 |
+
"sampling_rate": 16000
|
| 14 |
+
}
|
processor_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"audio_processor": {
|
| 3 |
+
"feature_extractor_type": "GraniteSpeechFeatureExtractor",
|
| 4 |
+
"melspec_kwargs": {
|
| 5 |
+
"hop_length": 160,
|
| 6 |
+
"n_fft": 512,
|
| 7 |
+
"n_mels": 80,
|
| 8 |
+
"sample_rate": 16000,
|
| 9 |
+
"win_length": 400
|
| 10 |
+
},
|
| 11 |
+
"projector_downsample_rate": 5,
|
| 12 |
+
"projector_window_size": 15,
|
| 13 |
+
"sampling_rate": 16000
|
| 14 |
+
},
|
| 15 |
+
"audio_token": "<|audio|>",
|
| 16 |
+
"processor_class": "GraniteSpeechProcessor"
|
| 17 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|end_of_text|>",
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|end_of_text|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"is_local": false,
|
| 9 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 10 |
+
"pad_token": "<|pad|>",
|
| 11 |
+
"padding_side": "left",
|
| 12 |
+
"processor_class": "GraniteSpeechProcessor",
|
| 13 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 14 |
+
"unk_token": "<|unk|>",
|
| 15 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}USER: {{ message['content'] }}\n ASSISTANT:{% elif message['role'] == 'assistant' %}{{ message['content'] }}{% endif %}{% endfor %}"
|
| 16 |
+
}
|