Skip to content

feat(transcribe): add --speech_model flag #124

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

Open
megatron0000 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat(transcribe): add --speech_model flag #124

Show file tree
Hide file tree
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
4 changes: 4 additions & 0 deletions cmd/transcribe.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,6 +129,9 @@ var transcribeCmd = &cobra.Command{
}
params.SummaryModel = summaryModel
}

speechModel, _ := cmd.Flags().GetString("speech_model")
params.SpeechModel = &speechModel
}

if params.RedactPii {
Expand Down Expand Up @@ -278,6 +281,7 @@ func init() {
transcribeCmd.PersistentFlags().StringP("webhook_url", "w", "", "Receive a webhook once your transcript is complete.")
transcribeCmd.PersistentFlags().StringP("word_boost", "k", "", "The value of this flag MUST be used surrounded by quotes. Any term included will have its likelihood of being transcribed boosted.")
transcribeCmd.PersistentFlags().StringP("summary_model", "q", "informative", "The model used to generate the summary.")
transcribeCmd.PersistentFlags().StringP("speech_model", "", "", "The speech model to use for the transcription. Allowed values: see https://www.assemblyai.com/docs/api-reference/transcripts/submit#request.body.speech_model")

transcribeCmd.Flags().Bool("test", false, "Flag for test executing purpose")
transcribeCmd.Flags().MarkHidden("test")
Expand Down
4 changes: 4 additions & 0 deletions main_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,6 +103,7 @@ func TestTranscribeWithFlags(t *testing.T) {
"--speaker_labels",
"--summarization",
"--topic_detection",
"--speech_model=nano",
"-p=false",
"-j",
"--test",
Expand Down Expand Up @@ -147,6 +148,9 @@ func TestTranscribeWithFlags(t *testing.T) {
if *result.IabCategories != true {
t.Errorf("Expected IAB Categories(Topic detection) true, got false.")
}
if result.SpeechModel == nil || *result.SpeechModel != "nano" {
t.Errorf("Expected speech_model to be 'nano', got '%v'.", result.SpeechModel)
}
}

func TestTranscribeRestrictions(t *testing.T) {
Expand Down
2 changes: 2 additions & 0 deletions schemas/types.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -62,6 +62,7 @@ type TranscriptResponse struct {
SentimentAnalysis *bool `json:"sentiment_analysis,omitempty"`
SentimentAnalysisResults *[]SentimentAnalysisResult `json:"sentiment_analysis_results,omitempty"`
SpeakerLabels bool `json:"speaker_labels,omitempty"`
SpeechModel *string `json:"speech_model,omitempty"`
SpeedBoost *bool `json:"speed_boost,omitempty"`
Status *string `json:"status,omitempty"`
Summarization *bool `json:"summarization,omitempty"`
Expand Down Expand Up @@ -208,6 +209,7 @@ type TranscribeParams struct {
WebhookAuthHeaderValue string `json:"webhook_auth_header_value,omitempty"`
WebhookURL string `json:"webhook_url,omitempty"`
WordBoost []string `json:"word_boost,omitempty"`
SpeechModel *string `json:"speech_model,omitempty"`
}

type CustomSpelling struct {
Expand Down