Long Form ASR based on deep full-sequence convolutional neural networks, converting long audio data (within 5 hours) into text data.
- Provider
- iFlytek Open Platform
- Input summary
- {"name":"pd","type":"string","required":false,"description":"Domain personalization parameter","enum":["court","edu","finance","medical","tech","culture","isp","sport","gov","game","ecom","mil","com","life","ent","car"]}, {"name":"hotWord","type":"string","required":false,"description":"Hot words to improve recognition rate of professional vocabulary"}, {"name":"roleNum","type":"integer","required":false,"description":"Number of speakers, range 0-10, default 0 for blind separation"}, {"name":"audioUrl","type":"string","required":false,"description":"Audio URL external link address"}, {"name":"duration","type":"integer","required":true,"description":"Audio real duration"}, {"name":"fileName","type":"string","required":true,"description":"Audio file name, preferably with real file extension"}, {"name":"fileSize","type":"integer","required":true,"description":"Audio file size (bytes)"}, {"name":"language","type":"string","required":false,"description":"Language type","enum":["cn","en","ja","ko","ru","fr","es","vi","ar","de","it"]}
- Output summary
- Not available
- Billing
- 1
- Freshness
- Not available
- Verification
- Not available
