modelscope--funasr/.github/ISSUE_TEMPLATE/migration_benchmark.md

name, about, labels

name	about	labels
📊 Migration Benchmark Report	Share FunASR results when comparing against Whisper, OpenAI audio APIs, or cloud ASR	benchmark, showcase, needs triage

Thanks for benchmarking FunASR on your own audio. Migration reports help new users decide whether FunASR fits their language, domain, hardware, and deployment constraints.

If you need help debugging a failure, please use Bug Report or Deployment Help instead.

Summary

Baseline

• Baseline ASR (Whisper, Whisper large-v3, cloud provider, internal system, other):
• Baseline runtime or API:
• Baseline hardware or pricing tier:

FunASR setup

• FunASR version:
• Model(s):
• Runtime path (Python API, funasr-server, OpenAI API, Docker, WebSocket, vLLM, other):
• Device (cuda, cpu, mps):
• GPU / CPU:
• CUDA / PyTorch versions:
• Command or script used:

Audio set

• Number of files:
• Total audio duration:
• Language(s) / dialect(s):
• Domain (meeting, call-center, subtitle, lecture, media, noisy field audio, other):
• Speaker count range:
• Sample rate / format:
• Can any sample be shared publicly? yes/no

Results

Quality notes

Operational notes

• Model download / warmup time:
• Steady-state throughput:
• Memory usage:
• Failed files or error rate:
• Deployment blockers:

Links or artifacts

What should FunASR improve next?