Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Adds Whisper model #18819

Merged
merged 1 commit into from
Dec 18, 2024
Merged

Adds Whisper model #18819

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
150 changes: 150 additions & 0 deletions src/content/workers-ai-models/whisper-large-v3-turbo.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,150 @@
{
"id": "200f0812-148c-48c1-915d-fb3277a94a08",
"source": 1,
"name": "@cf/openai/whisper-large-v3-turbo",
"description": "Whisper is a pre-trained model for automatic speech recognition (ASR) and speech translation. ",
"task": {
"id": "dfce1c48-2a81-462e-a7fd-de97ce985207",
"name": "Automatic Speech Recognition",
"description": "Automatic speech recognition (ASR) models convert a speech signal, typically an audio input, to text."
},
"tags": [],
"properties": [
{
"property_id": "beta",
"value": "true"
}
],
"schema": {
"input": {
"type": "object",
"properties": {
"audio": {
"type": "string",
"description": "Base64 encoded value of the audio data."
},
"task": {
"type": "string",
"default": "transcribe",
"description": "Supported tasks are 'translate' or 'transcribe'."
},
"language": {
"type": "string",
"default": "en",
"description": "The language of the audio being transcribed or translated."
},
"vad_filter": {
"type": "string",
"default": "false",
"description": "Preprocess the audio with a voice activity detection model."
},
"initial_prompt": {
"type": "string",
"description": "A text prompt to help provide context to the model on the contents of the audio."
},
"prefix": {
"type": "string",
"description": "The prefix it appended the the beginning of the output of the transcription and can guide the transcription result."
}
},
"required": [
"audio"
]
},
"output": {
"type": "object",
"contentType": "application/json",
"properties": {
"transcription_info": {
"type": "object",
"properties": {
"language": {
"type": "string",
"description": "The language of the audio being transcribed or translated."
},
"language_probability": {
"type": "number",
"description": "The confidence level or probability of the detected language being accurate, represented as a decimal between 0 and 1."
},
"duration": {
"type": "number",
"description": "The total duration of the original audio file, in seconds."
},
"duration_after_vad": {
"type": "number",
"description": "The duration of the audio after applying Voice Activity Detection (VAD) to remove silent or irrelevant sections, in seconds."
}
}
},
"text": {
"type": "string",
"description": "The complete transcription of the audio."
},
"word_count": {
"type": "number",
"description": "The total number of words in the transcription."
},
"segments": {
"type": "object",
"properties": {
"start": {
"type": "number",
"description": "The starting time of the segment within the audio, in seconds."
},
"end": {
"type": "number",
"description": "The ending time of the segment within the audio, in seconds."
},
"text": {
"type": "string",
"description": "The transcription of the segment."
},
"temperature": {
"type": "number",
"description": "The temperature used in the decoding process, controlling randomness in predictions. Lower values result in more deterministic outputs."
},
"avg_logprob": {
"type": "number",
"description": "The average log probability of the predictions for the words in this segment, indicating overall confidence."
},
"compression_ratio": {
"type": "number",
"description": "The compression ratio of the input to the output, measuring how much the text was compressed during the transcription process."
},
"no_speech_prob": {
"type": "number",
"description": "The probability that the segment contains no speech, represented as a decimal between 0 and 1."
},
"words": {
"type": "array",
"items": {
"type": "object",
"properties": {
"word": {
"type": "string",
"description": "The individual word transcribed from the audio."
},
"start": {
"type": "number",
"description": "The starting time of the word within the audio, in seconds."
},
"end": {
"type": "number",
"description": "The ending time of the word within the audio, in seconds."
}
}
}
}
}
},
"vtt": {
"type": "string",
"description": "The transcription in WebVTT format, which includes timing and text information for use in subtitles."
}
},
"required": [
"text"
]
}
}
}
Loading