Speech2Text
Speech2Text
Source code in Agent/modules/speech_to_text/speech2text.py
18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 |
|
__init__(model_name='whisper', model_size='small', multi_language=True)
Initialize the translator Args: model_name (str): The name of the model to use model_size (str): The size of the model to use multi_language (bool): If the model is multi-language
Source code in Agent/modules/speech_to_text/speech2text.py
21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 |
|
handle_task(task)
Parameters:
Name | Type | Description | Default |
---|---|---|---|
task
|
Task
|
The task to process |
required |
Returns:
Type | Description |
---|---|
Task
|
The processed task |
Source code in Agent/modules/speech_to_text/speech2text.py
108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 |
|
locate_audio_file(uid, sequence_index, end_time)
staticmethod
Locate the audio file Args: uid (str): The uid sequence_index (str): The sequence index end_time (str): The end time
Returns:
Type | Description |
---|---|
The audio file (str): The audio file |
Source code in Agent/modules/speech_to_text/speech2text.py
42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 |
|
translate(message, task)
This is the key function to translate the audio to text Args: message (dict): The message to translate task (Task): The task
Returns:
Name | Type | Description |
---|---|---|
task |
Task
|
The task |
Source code in Agent/modules/speech_to_text/speech2text.py
66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 |
|