Skip to content

Commit 2892851

Browse files
committed
how to use content assessment via LLM
1 parent 62aeeaf commit 2892851

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

articles/ai-services/speech-service/how-to-pronunciation-assessment.md

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1134,7 +1134,7 @@ The user and system messages are used to set the context for the chat model. In
11341134
},
11351135
{
11361136
"role": "user",
1137-
"content": "Example1: this essay: \"sampleSentence1\" has vocabulary and grammar scores of 80 and 80, respectively. Example2: this essay: \"sampleSentence2\" has vocabulary and grammar scores of 40 and 43, respectively. Example3: this essay: \"sampleSentence3\" has vocabulary and grammar scores of 50 and 50, respectively. The essay for you to score is \"sendText\", and the title is \"topic\". The transcript is from speech recognition so that please first add punctuations when needed, remove duplicates and unnecessary un uh from oral speech, then find all the misuse of words and grammar errors in this essay, find advanced words and grammar usages, and finally give scores based on this information. Please only respond as this format {\"vocabulary\": *.*(0-100), \"grammar\": *.*(0-100)}, \"topic\": *.*(0-100)}. [THE TRANSCRIPT FROM SPEECH RECOGNITION IS REDACTED FOR BREVITY]"
1137+
"content": "Example1: this essay: \"sampleSentence1\" has vocabulary and grammar scores of ** and **, respectively. Example2: this essay: \"sampleSentence2\" has vocabulary and grammar scores of ** and **, respectively. Example3: this essay: \"sampleSentence3\" has vocabulary and grammar scores of ** and **, respectively. The essay for you to score is \"sendText\", and the title is \"topic\". The transcript is from speech recognition so that please first add punctuations when needed, remove duplicates and unnecessary un uh from oral speech, then find all the misuse of words and grammar errors in this essay, find advanced words and grammar usages, and finally give scores based on this information. Please only respond as this format {\"vocabulary\": *.*(0-100), \"grammar\": *.*(0-100)}, \"topic\": *.*(0-100)}. [THE TRANSCRIPT FROM SPEECH RECOGNITION IS REDACTED FOR BREVITY]"
11381138
}
11391139
]
11401140
}

0 commit comments

Comments
 (0)