Hi @rsarosh,
Welcome and thank you for reaching out to our community.
Google cloud has automated systems to keep track of events and activities within the platform hence it is less likely that specific manual monitoring from google is necessary.
A couple of reasons come to mind regarding this long task duration:
- The audio file may be a bit complex to transcribe, say having multiple speakers, strong background noises or challenging accents that can cause longer transcription to ensure accuracy
- It is possible that your machine resources are heavily utilized hence the transcription requests are being queued behind other tasks until these resources are made available
Although rare, service interruptions can also be the cause of this, if so, you can always reach out to Cloud Speech-to-Text support for better assistance.
Adding this "Best practices to provide data to the Speech-to-Text API" document as reference for optimization insights.
LinkedIn
Twitter
