Skip to content

Speakr is a personal, self-hosted web application designed for transcribing audio recordings

Python

fix: FunASR follow-up - restore UTF-8 encoding in env example (BOM + 6 mojibake lines), align schema defaults with runtime defaults, drop stray lowercase env read, dedupe download log line, floor poll_interval at 1

Murtaza Nasir41d964cdcc84
diff --git a/config/env.transcription.example b/config/env.transcription.example
index e5a31b51..898139cb 100644
--- a/config/env.transcription.example
+++ b/config/env.transcription.example
@@ -1,4 +1,4 @@
-# =============================================================================
+# =============================================================================
# Transcription Connector Configuration
# =============================================================================
#
@@ -265,11 +265,11 @@ TRANSCRIPTION_MODEL=gpt-4o-transcribe-diarize
# CHUNKING CONFIGURATION (For large files)
# =============================================================================
# Chunking is now connector-aware with this priority:
-# 1. Connector handles internally (openai_transcribe, asr_endpoint, mistral) 鈫?No app chunking
-# 2. ENABLE_CHUNKING=false 鈫?Disable chunking (only affects openai_whisper)
-# 3. CHUNK_LIMIT set 鈫?Use your settings
-# 4. Connector defaults 鈫?Use connector's recommended limits
-# 5. App default 鈫?20MB size-based
+# 1. Connector handles internally (openai_transcribe, asr_endpoint, mistral) → No app chunking
+# 2. ENABLE_CHUNKING=false → Disable chunking (only affects openai_whisper)
+# 3. CHUNK_LIMIT set → Use your settings
+# 4. Connector defaults → Use connector's recommended limits
+# 5. App default → 20MB size-based
#
# For openai_transcribe/asr_endpoint/mistral: These settings are IGNORED (connector handles it)
# For openai_whisper: These settings control chunking behavior
@@ -505,7 +505,7 @@ VIDEO_RETENTION=false
# Send original video files directly to ASR without extracting audio.
# Useful for custom ASR backends that handle video internally (e.g., multi-track audio extraction).
# When enabled, video files bypass audio extraction, codec conversion, and chunking.
-# Only affects video files 鈥?audio uploads are processed normally.
+# Only affects video files — audio uploads are processed normally.
# Default: false
# VIDEO_PASSTHROUGH_ASR=false
diff --git a/src/services/transcription/connectors/alibaba_funasr.py b/src/services/transcription/connectors/alibaba_funasr.py
index 137788b3..12cc813e 100644
--- a/src/services/transcription/connectors/alibaba_funasr.py
+++ b/src/services/transcription/connectors/alibaba_funasr.py
@@ -77,7 +77,7 @@ class AlibabaFunASRConnector(BaseTranscriptionConnector):
self.api_key = api_key
self.model = model
self._config_timeout = config.get('timeout', 1800)
- self.poll_interval = config.get('poll_interval', 10)
+ self.poll_interval = max(1, int(config.get('poll_interval', 10) or 10))
self.default_diarize = config.get('diarize', False)
self.disfluency_removal_enabled = config.get('disfluency_removal_enabled', False)
self.timestamp_alignment_enabled = config.get('timestamp_alignment_enabled', False)
@@ -106,7 +106,7 @@ class AlibabaFunASRConnector(BaseTranscriptionConnector):
@property
def timeout(self):
"""Get timeout with env-var override, falling back to config default."""
- env_timeout = os.environ.get('ASR_TIMEOUT') or os.environ.get('asr_timeout_seconds')
+ env_timeout = os.environ.get('ASR_TIMEOUT')
if env_timeout:
try:
return int(env_timeout)
@@ -351,10 +351,6 @@ class AlibabaFunASRConnector(BaseTranscriptionConnector):
if not transcription_url:
raise TranscriptionError("FunASR response missing transcription_url")
- logger.info(
- "Downloading transcription result: %s",
- _redact_url(transcription_url),
- )
transcription_data = self._download_transcription_result(transcription_url)
return self._parse_transcription_data(transcription_data)
@@ -528,12 +524,12 @@ class AlibabaFunASRConnector(BaseTranscriptionConnector):
},
"diarize": {
"type": "boolean",
- "default": True,
+ "default": False,
"description": "Enable speaker diarization"
},
"disfluency_removal_enabled": {
"type": "boolean",
- "default": True,
+ "default": False,
"description": "Filter filler words"
},
"timestamp_alignment_enabled": {